remove noop code

.travis.yml

@@ -11,4 +11,4 @@ install:
 
 script:
     - flake8 . --show-source --statistics
-    - docker run baselines-test pytest -v .
+    - docker run baselines-test pytest -v --forked .

README.md

@@ -89,7 +89,7 @@ python -m baselines.run --alg=ppo2 --env=Humanoid-v2 --network=mlp --num_timeste
 will set entropy coefficient to 0.1, and construct fully connected network with 3 layers with 32 hidden units in each, and create a separate network for value function estimation (so that its parameters are not shared with the policy network, but the structure is the same)
 
 See docstrings in [common/models.py](baselines/common/models.py) for description of network parameters for each type of model, and 
-docstring for [baselines/ppo2/ppo2.py/learn()](baselines/ppo2/ppo2.py#L152) for the description of the ppo2 hyperparameters. 
+docstring for [baselines/ppo2/ppo2.py/learn()](baselines/ppo2/ppo2.py#L152) for the description of the ppo2 hyperparamters. 
 
 ### Example 2. DQN on Atari 
 DQN with Atari is at this point a classics of benchmarks. To run the baselines implementation of DQN on Atari Pong:

baselines/a2c/a2c.py

@@ -11,8 +11,6 @@ from baselines.common.policies import build_policy
 
 from baselines.a2c.utils import Scheduler, find_trainable_variables
 from baselines.a2c.runner import Runner
-from baselines.ppo2.ppo2 import safemean
-from collections import deque
 
 from tensorflow import losses
 
@@ -197,7 +195,6 @@ def learn(
 
     # Instantiate the runner object
     runner = Runner(env, model, nsteps=nsteps, gamma=gamma)
-    epinfobuf = deque(maxlen=100)
 
     # Calculate the batch_size
     nbatch = nenvs*nsteps
@@ -207,8 +204,7 @@ def learn(
 
     for update in range(1, total_timesteps//nbatch+1):
         # Get mini batch of experiences
-        obs, states, rewards, masks, actions, values, epinfos = runner.run()
-        epinfobuf.extend(epinfos)
+        obs, states, rewards, masks, actions, values = runner.run()
 
         policy_loss, value_loss, policy_entropy = model.train(obs, states, rewards, masks, actions, values)
         nseconds = time.time()-tstart
@@ -225,8 +221,6 @@ def learn(
             logger.record_tabular("policy_entropy", float(policy_entropy))
             logger.record_tabular("value_loss", float(value_loss))
             logger.record_tabular("explained_variance", float(ev))
-            logger.record_tabular("eprewmean", safemean([epinfo['r'] for epinfo in epinfobuf]))
-            logger.record_tabular("eplenmean", safemean([epinfo['l'] for epinfo in epinfobuf]))
             logger.dump_tabular()
     return model
 

baselines/a2c/runner.py

@@ -22,7 +22,6 @@ class Runner(AbstractEnvRunner):
         # We initialize the lists that will contain the mb of experiences
         mb_obs, mb_rewards, mb_actions, mb_values, mb_dones = [],[],[],[],[]
         mb_states = self.states
-        epinfos = []
         for n in range(self.nsteps):
             # Given observations, take action and value (V(s))
             # We already have self.obs because Runner superclass run self.obs[:] = env.reset() on init
@@ -35,10 +34,7 @@ class Runner(AbstractEnvRunner):
             mb_dones.append(self.dones)
 
             # Take actions in env and look the results
-            obs, rewards, dones, infos = self.env.step(actions)
-            for info in infos:
-                maybeepinfo = info.get('episode')
-                if maybeepinfo: epinfos.append(maybeepinfo)
+            obs, rewards, dones, _ = self.env.step(actions)
             self.states = states
             self.dones = dones
             self.obs = obs
@@ -73,4 +69,4 @@ class Runner(AbstractEnvRunner):
         mb_rewards = mb_rewards.flatten()
         mb_values = mb_values.flatten()
         mb_masks = mb_masks.flatten()
-        return mb_obs, mb_states, mb_rewards, mb_masks, mb_actions, mb_values, epinfos
+        return mb_obs, mb_states, mb_rewards, mb_masks, mb_actions, mb_values

baselines/acer/acer.py

@@ -75,8 +75,8 @@ class Model(object):
         train_ob_placeholder = tf.placeholder(dtype=ob_space.dtype, shape=(nenvs*(nsteps+1),) + ob_space.shape)
         with tf.variable_scope('acer_model', reuse=tf.AUTO_REUSE):
 
-            step_model = policy(nbatch=nenvs, nsteps=1, observ_placeholder=step_ob_placeholder, sess=sess)
-            train_model = policy(nbatch=nbatch, nsteps=nsteps, observ_placeholder=train_ob_placeholder, sess=sess)
+            step_model = policy(observ_placeholder=step_ob_placeholder, sess=sess)
+            train_model = policy(observ_placeholder=train_ob_placeholder, sess=sess)
 
 
         params = find_trainable_variables("acer_model")
@@ -94,7 +94,7 @@ class Model(object):
             return v
 
         with tf.variable_scope("acer_model", custom_getter=custom_getter, reuse=True):
-            polyak_model = policy(nbatch=nbatch, nsteps=nsteps, observ_placeholder=train_ob_placeholder, sess=sess)
+            polyak_model = policy(observ_placeholder=train_ob_placeholder, sess=sess)
 
         # Notation: (var) = batch variable, (var)s = seqeuence variable, (var)_i = variable index by action at step i
 

baselines/acktr/acktr.py

@@ -11,8 +11,6 @@ from baselines.common.tf_util import get_session, save_variables, load_variables
 from baselines.a2c.runner import Runner
 from baselines.a2c.utils import Scheduler, find_trainable_variables
 from baselines.acktr import kfac
-from baselines.ppo2.ppo2 import safemean
-from collections import deque
 
 
 class Model(object):
@@ -120,7 +118,6 @@ def learn(network, env, seed, total_timesteps=int(40e6), gamma=0.99, log_interva
         model.load(load_path)
 
     runner = Runner(env, model, nsteps=nsteps, gamma=gamma)
-    epinfobuf = deque(maxlen=100)
     nbatch = nenvs*nsteps
     tstart = time.time()
     coord = tf.train.Coordinator()
@@ -130,8 +127,7 @@ def learn(network, env, seed, total_timesteps=int(40e6), gamma=0.99, log_interva
         enqueue_threads = []
 
     for update in range(1, total_timesteps//nbatch+1):
-        obs, states, rewards, masks, actions, values, epinfos = runner.run()
-        epinfobuf.extend(epinfos)
+        obs, states, rewards, masks, actions, values = runner.run()
         policy_loss, value_loss, policy_entropy = model.train(obs, states, rewards, masks, actions, values)
         model.old_obs = obs
         nseconds = time.time()-tstart
@@ -145,8 +141,6 @@ def learn(network, env, seed, total_timesteps=int(40e6), gamma=0.99, log_interva
             logger.record_tabular("policy_loss", float(policy_loss))
             logger.record_tabular("value_loss", float(value_loss))
             logger.record_tabular("explained_variance", float(ev))
-            logger.record_tabular("eprewmean", safemean([epinfo['r'] for epinfo in epinfobuf]))
-            logger.record_tabular("eplenmean", safemean([epinfo['l'] for epinfo in epinfobuf]))
             logger.dump_tabular()
 
         if save_interval and (update % save_interval == 0 or update == 1) and logger.get_dir():

baselines/bench/benchmarks.py

@@ -20,7 +20,7 @@ def register_benchmark(benchmark):
     if 'tasks' in benchmark:
         for t in benchmark['tasks']:
             if 'desc' not in t:
-                t['desc'] = remove_version_re.sub('', t.get('env_id', t.get('id')))
+                t['desc'] = remove_version_re.sub('', t['env_id'])
     _BENCHMARKS.append(benchmark)
 
 
@@ -156,10 +156,9 @@ register_benchmark({
 
 # HER DDPG
 
-_fetch_tasks = ['FetchReach-v1', 'FetchPush-v1', 'FetchSlide-v1']
 register_benchmark({
-    'name': 'Fetch1M',
-    'description': 'Fetch* benchmarks for 1M timesteps',
-    'tasks': [{'trials': 6, 'env_id': env_id, 'num_timesteps': int(1e6)} for env_id in _fetch_tasks]
+    'name': 'HerDdpg',
+    'description': 'Smoke-test only benchmark of HER',
+    'tasks': [{'trials': 1, 'env_id': 'FetchReach-v1'}]
 })
 

baselines/bench/monitor.py

@@ -16,13 +16,11 @@ class Monitor(Wrapper):
     def __init__(self, env, filename, allow_early_resets=False, reset_keywords=(), info_keywords=()):
         Wrapper.__init__(self, env=env)
         self.tstart = time.time()
-        if filename:
-            self.results_writer = ResultsWriter(filename,
-                header={"t_start": time.time(), 'env_id' : env.spec and env.spec.id},
-                extra_keys=reset_keywords + info_keywords
-            )
-        else:
-            self.results_writer = None
+        self.results_writer = ResultsWriter(
+            filename,
+            header={"t_start": time.time(), 'env_id' : env.spec and env.spec.id},
+            extra_keys=reset_keywords + info_keywords
+        )
         self.reset_keywords = reset_keywords
         self.info_keywords = info_keywords
         self.allow_early_resets = allow_early_resets
@@ -70,9 +68,8 @@ class Monitor(Wrapper):
             self.episode_lengths.append(eplen)
             self.episode_times.append(time.time() - self.tstart)
             epinfo.update(self.current_reset_info)
-            if self.results_writer:
-                self.results_writer.write_row(epinfo)
-            assert isinstance(info, dict)
+            self.results_writer.write_row(epinfo)
+
             if isinstance(info, dict):
                 info['episode'] = epinfo
 
@@ -99,21 +96,24 @@ class LoadMonitorResultsError(Exception):
 
 
 class ResultsWriter(object):
-    def __init__(self, filename, header='', extra_keys=()):
+    def __init__(self, filename=None, header='', extra_keys=()):
         self.extra_keys = extra_keys
-        assert filename is not None
-        if not filename.endswith(Monitor.EXT):
-            if osp.isdir(filename):
-                filename = osp.join(filename, Monitor.EXT)
-            else:
-                filename = filename + "." + Monitor.EXT
-        self.f = open(filename, "wt")
-        if isinstance(header, dict):
-            header = '# {} \n'.format(json.dumps(header))
-        self.f.write(header)
-        self.logger = csv.DictWriter(self.f, fieldnames=('r', 'l', 't')+tuple(extra_keys))
-        self.logger.writeheader()
-        self.f.flush()
+        if filename is None:
+            self.f = None
+            self.logger = None
+        else:
+            if not filename.endswith(Monitor.EXT):
+                if osp.isdir(filename):
+                    filename = osp.join(filename, Monitor.EXT)
+                else:
+                    filename = filename + "." + Monitor.EXT
+            self.f = open(filename, "wt")
+            if isinstance(header, dict):
+                header = '# {} \n'.format(json.dumps(header))
+            self.f.write(header)
+            self.logger = csv.DictWriter(self.f, fieldnames=('r', 'l', 't')+tuple(extra_keys))
+            self.logger.writeheader()
+            self.f.flush()
 
     def write_row(self, epinfo):
         if self.logger:
@@ -121,6 +121,7 @@ class ResultsWriter(object):
             self.f.flush()
 
 
+
 def get_monitor_files(dir):
     return glob(osp.join(dir, "*" + Monitor.EXT))
 

baselines/common/atari_wrappers.py

@@ -6,8 +6,6 @@ import gym
 from gym import spaces
 import cv2
 cv2.ocl.setUseOpenCL(False)
-from .wrappers import TimeLimit
-
 
 class NoopResetEnv(gym.Wrapper):
     def __init__(self, env, noop_max=30):
@@ -221,15 +219,16 @@ class LazyFrames(object):
         return len(self._force())
 
     def __getitem__(self, i):
-        return self._force()[..., i]
+        return self._force()[i]
 
-def make_atari(env_id, max_episode_steps=None):
+def make_atari(env_id, timelimit=True):
+    # XXX(john): remove timelimit argument after gym is upgraded to allow double wrapping
     env = gym.make(env_id)
+    if not timelimit:
+        env = env.env
     assert 'NoFrameskip' in env.spec.id
     env = NoopResetEnv(env, noop_max=30)
     env = MaxAndSkipEnv(env, skip=4)
-    if max_episode_steps is not None:
-        env = TimeLimit(env, max_episode_steps=max_episode_steps)
     return env
 
 def wrap_deepmind(env, episode_life=True, clip_rewards=True, frame_stack=False, scale=False):

baselines/common/cmd_util.py

@@ -18,31 +18,22 @@ from baselines.common.vec_env.subproc_vec_env import SubprocVecEnv
 from baselines.common.vec_env.dummy_vec_env import DummyVecEnv
 from baselines.common import retro_wrappers
 
-def make_vec_env(env_id, env_type, num_env, seed,
-                 wrapper_kwargs=None,
-                 start_index=0,
-                 reward_scale=1.0,
-                 flatten_dict_observations=True,
-                 gamestate=None):
+def make_vec_env(env_id, env_type, num_env, seed, wrapper_kwargs=None, start_index=0, reward_scale=1.0, gamestate=None):
     """
     Create a wrapped, monitored SubprocVecEnv for Atari and MuJoCo.
     """
-    wrapper_kwargs = wrapper_kwargs or {}
+    if wrapper_kwargs is None: wrapper_kwargs = {}
     mpi_rank = MPI.COMM_WORLD.Get_rank() if MPI else 0
     seed = seed + 10000 * mpi_rank if seed is not None else None
-    logger_dir = logger.get_dir()
     def make_thunk(rank):
         return lambda: make_env(
             env_id=env_id,
             env_type=env_type,
-            mpi_rank=mpi_rank,
-            subrank=rank,
+            subrank = rank,
             seed=seed,
             reward_scale=reward_scale,
             gamestate=gamestate,
-            flatten_dict_observations=flatten_dict_observations,
-            wrapper_kwargs=wrapper_kwargs,
-            logger_dir=logger_dir
+            wrapper_kwargs=wrapper_kwargs
         )
 
     set_global_seeds(seed)
@@ -52,8 +43,8 @@ def make_vec_env(env_id, env_type, num_env, seed,
         return DummyVecEnv([make_thunk(start_index)])
 
 
-def make_env(env_id, env_type, mpi_rank=0, subrank=0, seed=None, reward_scale=1.0, gamestate=None, flatten_dict_observations=True, wrapper_kwargs=None, logger_dir=None):
-    wrapper_kwargs = wrapper_kwargs or {}
+def make_env(env_id, env_type, subrank=0, seed=None, reward_scale=1.0, gamestate=None, wrapper_kwargs={}):
+    mpi_rank = MPI.COMM_WORLD.Get_rank() if MPI else 0
     if env_type == 'atari':
         env = make_atari(env_id)
     elif env_type == 'retro':
@@ -63,20 +54,14 @@ def make_env(env_id, env_type, mpi_rank=0, subrank=0, seed=None, reward_scale=1.
     else:
         env = gym.make(env_id)
 
-    if flatten_dict_observations and isinstance(env.observation_space, gym.spaces.Dict):
-        keys = env.observation_space.spaces.keys()
-        env = gym.wrappers.FlattenDictWrapper(env, dict_keys=list(keys))
-
     env.seed(seed + subrank if seed is not None else None)
     env = Monitor(env,
-                  logger_dir and os.path.join(logger_dir, str(mpi_rank) + '.' + str(subrank)),
+                  logger.get_dir() and os.path.join(logger.get_dir(), str(mpi_rank) + '.' + str(subrank)),
                   allow_early_resets=True)
 
     if env_type == 'atari':
         env = wrap_deepmind(env, **wrapper_kwargs)
     elif env_type == 'retro':
-        if 'frame_stack' not in wrapper_kwargs:
-            wrapper_kwargs['frame_stack'] = 1
         env = retro_wrappers.wrap_deepmind_retro(env, **wrapper_kwargs)
 
     if reward_scale != 1:
@@ -138,7 +123,6 @@ def common_arg_parser():
     """
     parser = arg_parser()
     parser.add_argument('--env', help='environment ID', type=str, default='Reacher-v2')
-    parser.add_argument('--env_type', help='type of environment, used when the environment type cannot be automatically determined', type=str)
     parser.add_argument('--seed', help='RNG seed', type=int, default=None)
     parser.add_argument('--alg', help='Algorithm', type=str, default='ppo2')
     parser.add_argument('--num_timesteps', type=float, default=1e6),

baselines/common/distributions.py

@@ -75,8 +75,7 @@ class CategoricalPdType(PdType):
 
 class MultiCategoricalPdType(PdType):
     def __init__(self, nvec):
-        self.ncats = nvec.astype('int32')
-        assert (self.ncats > 0).all()
+        self.ncats = nvec
     def pdclass(self):
         return MultiCategoricalPd
     def pdfromflat(self, flat):
@@ -206,8 +205,7 @@ class CategoricalPd(Pd):
 class MultiCategoricalPd(Pd):
     def __init__(self, nvec, flat):
         self.flat = flat
-        self.categoricals = list(map(CategoricalPd,
-            tf.split(flat, np.array(nvec, dtype=np.int32), axis=-1)))
+        self.categoricals = list(map(CategoricalPd, tf.split(flat, nvec, axis=-1)))
     def flatparam(self):
         return self.flat
     def mode(self):

baselines/common/misc_util.py

@@ -13,6 +13,27 @@ def zipsame(*seqs):
     return zip(*seqs)
 
 
+def unpack(seq, sizes):
+    """
+    Unpack 'seq' into a sequence of lists, with lengths specified by 'sizes'.
+    None = just one bare element, not a list
+
+    Example:
+    unpack([1,2,3,4,5,6], [3,None,2]) -> ([1,2,3], 4, [5,6])
+    """
+    seq = list(seq)
+    it = iter(seq)
+    assert sum(1 if s is None else s for s in sizes) == len(seq), "Trying to unpack %s into %s" % (seq, sizes)
+    for size in sizes:
+        if size is None:
+            yield it.__next__()
+        else:
+            li = []
+            for _ in range(size):
+                li.append(it.__next__())
+            yield li
+
+
 class EzPickle(object):
     """Objects that are pickled and unpickled via their constructor
     arguments.

baselines/common/mpi_adam_optimizer.py

@@ -1,11 +1,6 @@
 import numpy as np
 import tensorflow as tf
-from baselines.common import tf_util as U
-from baselines.common.tests.test_with_mpi import with_mpi
-try:
-    from mpi4py import MPI
-except ImportError:
-    MPI = None
+from mpi4py import MPI
 
 class MpiAdamOptimizer(tf.train.AdamOptimizer):
     """Adam optimizer that averages gradients across mpi processes."""
@@ -18,61 +13,19 @@ class MpiAdamOptimizer(tf.train.AdamOptimizer):
         flat_grad = tf.concat([tf.reshape(g, (-1,)) for g, v in grads_and_vars], axis=0)
         shapes = [v.shape.as_list() for g, v in grads_and_vars]
         sizes = [int(np.prod(s)) for s in shapes]
+
         num_tasks = self.comm.Get_size()
         buf = np.zeros(sum(sizes), np.float32)
-        countholder = [0] # Counts how many times _collect_grads has been called
-        stat = tf.reduce_sum(grads_and_vars[0][1]) # sum of first variable
-        def _collect_grads(flat_grad, np_stat):
+
+        def _collect_grads(flat_grad):
             self.comm.Allreduce(flat_grad, buf, op=MPI.SUM)
             np.divide(buf, float(num_tasks), out=buf)
-            if countholder[0] % 100 == 0:
-                check_synced(np_stat, self.comm)
-            countholder[0] += 1
             return buf
 
-        avg_flat_grad = tf.py_func(_collect_grads, [flat_grad, stat], tf.float32)
+        avg_flat_grad = tf.py_func(_collect_grads, [flat_grad], tf.float32)
         avg_flat_grad.set_shape(flat_grad.shape)
         avg_grads = tf.split(avg_flat_grad, sizes, axis=0)
         avg_grads_and_vars = [(tf.reshape(g, v.shape), v)
                     for g, (_, v) in zip(avg_grads, grads_and_vars)]
+
         return avg_grads_and_vars
-
-def check_synced(localval, comm=None):
-    """
-    It's common to forget to initialize your variables to the same values, or
-    (less commonly) if you update them in some other way than adam, to get them out of sync.
-    This function checks that variables on all MPI workers are the same, and raises
-    an AssertionError otherwise
-
-    Arguments:
-        comm: MPI communicator
-        localval: list of local variables (list of variables on current worker to be compared with the other workers)
-    """
-    comm = comm or MPI.COMM_WORLD
-    vals = comm.gather(localval)
-    if comm.rank == 0:
-        assert all(val==vals[0] for val in vals[1:])
-
-
-@with_mpi(timeout=5)
-def test_nonfreeze():
-    np.random.seed(0)
-    tf.set_random_seed(0)
-
-    a = tf.Variable(np.random.randn(3).astype('float32'))
-    b = tf.Variable(np.random.randn(2,5).astype('float32'))
-    loss = tf.reduce_sum(tf.square(a)) + tf.reduce_sum(tf.sin(b))
-
-    stepsize = 1e-2
-    # for some reason the session config with inter_op_parallelism_threads was causing
-    # nested sess.run calls to freeze
-    config = tf.ConfigProto(inter_op_parallelism_threads=1)
-    sess = U.get_session(config=config)
-    update_op = MpiAdamOptimizer(comm=MPI.COMM_WORLD, learning_rate=stepsize).minimize(loss)
-    sess.run(tf.global_variables_initializer())
-    losslist_ref = []
-    for i in range(100):
-        l,_ = sess.run([loss, update_op])
-        print(i, l)
-        losslist_ref.append(l)
-

baselines/common/mpi_util.py

@@ -1,16 +1,9 @@
 from collections import defaultdict
+from mpi4py import MPI
 import os, numpy as np
 import platform
 import shutil
 import subprocess
-import warnings
-import sys
-
-try:
-    from mpi4py import MPI
-except ImportError:
-    MPI = None
-
 
 def sync_from_root(sess, variables, comm=None):
     """
@@ -20,10 +13,15 @@ def sync_from_root(sess, variables, comm=None):
       variables: all parameter variables including optimizer's
     """
     if comm is None: comm = MPI.COMM_WORLD
-    import tensorflow as tf
-    values = comm.bcast(sess.run(variables))
-    sess.run([tf.assign(var, val)
-        for (var, val) in zip(variables, values)])
+    rank = comm.Get_rank()
+    for var in variables:
+        if rank == 0:
+            comm.Bcast(sess.run(var))
+        else:
+            import tensorflow as tf
+            returned_var = np.empty(var.shape, dtype='float32')
+            comm.Bcast(returned_var)
+            sess.run(tf.assign(var, returned_var))
 
 def gpu_count():
     """
@@ -36,15 +34,13 @@ def gpu_count():
 
 def setup_mpi_gpus():
     """
-    Set CUDA_VISIBLE_DEVICES to MPI rank if not already set
+    Set CUDA_VISIBLE_DEVICES using MPI.
     """
-    if 'CUDA_VISIBLE_DEVICES' not in os.environ:
-        if sys.platform == 'darwin': # This Assumes if you're on OSX you're just
-            ids = []                 # doing a smoke test and don't want GPUs
-        else:
-            lrank, _lsize = get_local_rank_size(MPI.COMM_WORLD)
-            ids = [lrank]
-        os.environ["CUDA_VISIBLE_DEVICES"] = ",".join(map(str, ids))
+    num_gpus = gpu_count()
+    if num_gpus == 0:
+        return
+    local_rank, _ = get_local_rank_size(MPI.COMM_WORLD)
+    os.environ['CUDA_VISIBLE_DEVICES'] = str(local_rank % num_gpus)
 
 def get_local_rank_size(comm):
     """
@@ -85,9 +81,6 @@ def share_file(comm, path):
     comm.Barrier()
 
 def dict_gather(comm, d, op='mean', assert_all_have_data=True):
-    """
-    Perform a reduction operation over dicts
-    """
     if comm is None: return d
     alldicts = comm.allgather(d)
     size = comm.size
@@ -106,28 +99,3 @@ def dict_gather(comm, d, op='mean', assert_all_have_data=True):
         else:
             assert 0, op
     return result
-
-def mpi_weighted_mean(comm, local_name2valcount):
-    """
-    Perform a weighted average over dicts that are each on a different node
-    Input: local_name2valcount: dict mapping key -> (value, count)
-    Returns: key -> mean
-    """
-    all_name2valcount = comm.gather(local_name2valcount)
-    if comm.rank == 0:
-        name2sum = defaultdict(float)
-        name2count = defaultdict(float)
-        for n2vc in all_name2valcount:
-            for (name, (val, count)) in n2vc.items():
-                try:
-                    val = float(val)
-                except ValueError:
-                    if comm.rank == 0:
-                        warnings.warn('WARNING: tried to compute mean on non-float {}={}'.format(name, val))
-                else:
-                    name2sum[name] += val * count
-                    name2count[name] += count
-        return {name : name2sum[name] / name2count[name] for name in name2sum}
-    else:
-        return {}
-

baselines/common/plot_util.py

@@ -168,7 +168,6 @@ def load_results(root_dir_or_dirs, enable_progress=True, enable_monitor=True, ve
          - monitor - if enable_monitor is True, this field contains pandas dataframe with loaded monitor.csv file (or aggregate of all *.monitor.csv files in the directory)
          - progress - if enable_progress is True, this field contains pandas dataframe with loaded progress.csv file
     '''
-    import re
     if isinstance(root_dir_or_dirs, str):
         rootdirs = [osp.expanduser(root_dir_or_dirs)]
     else:
@@ -180,9 +179,7 @@ def load_results(root_dir_or_dirs, enable_progress=True, enable_monitor=True, ve
             if '-proc' in dirname:
                 files[:] = []
                 continue
-            monitor_re = re.compile(r'(\d+\.)?(\d+\.)?monitor\.csv')
-            if set(['metadata.json', 'monitor.json', 'progress.json', 'progress.csv']).intersection(files) or \
-               any([f for f in files if monitor_re.match(f)]):  # also match monitor files like 0.1.monitor.csv
+            if set(['metadata.json', 'monitor.json', 'monitor.csv', 'progress.json', 'progress.csv']).intersection(files):
                 # used to be uncommented, which means do not go deeper than current directory if any of the data files
                 # are found
                 # dirs[:] = []
@@ -248,7 +245,7 @@ def plot_results(
     figsize=None,
     legend_outside=False,
     resample=0,
-    smooth_step=1.0
+    smooth_step=1.0,
 ):
     '''
     Plot multiple Results objects

baselines/common/retro_wrappers.py

@@ -1,11 +1,25 @@
-from collections import deque
-import cv2
-cv2.ocl.setUseOpenCL(False)
-from .atari_wrappers import WarpFrame, ClipRewardEnv, FrameStack, ScaledFloatFrame
-from .wrappers import TimeLimit
+ # flake8: noqa F403, F405
+from .atari_wrappers import *
 import numpy as np
 import gym
 
+class TimeLimit(gym.Wrapper):
+    def __init__(self, env, max_episode_steps=None):
+        super(TimeLimit, self).__init__(env)
+        self._max_episode_steps = max_episode_steps
+        self._elapsed_steps = 0
+
+    def step(self, ac):
+        observation, reward, done, info = self.env.step(ac)
+        self._elapsed_steps += 1
+        if self._elapsed_steps >= self._max_episode_steps:
+            done = True
+            info['TimeLimit.truncated'] = True
+        return observation, reward, done, info
+
+    def reset(self, **kwargs):
+        self._elapsed_steps = 0
+        return self.env.reset(**kwargs)
 
 class StochasticFrameSkip(gym.Wrapper):
     def __init__(self, env, n, stickprob):
@@ -85,7 +99,7 @@ class Downsample(gym.ObservationWrapper):
         gym.ObservationWrapper.__init__(self, env)
         (oldh, oldw, oldc) = env.observation_space.shape
         newshape = (oldh//ratio, oldw//ratio, oldc)
-        self.observation_space = gym.spaces.Box(low=0, high=255,
+        self.observation_space = spaces.Box(low=0, high=255,
             shape=newshape, dtype=np.uint8)
 
     def observation(self, frame):
@@ -102,7 +116,7 @@ class Rgb2gray(gym.ObservationWrapper):
         """
         gym.ObservationWrapper.__init__(self, env)
         (oldh, oldw, _oldc) = env.observation_space.shape
-        self.observation_space = gym.spaces.Box(low=0, high=255,
+        self.observation_space = spaces.Box(low=0, high=255,
             shape=(oldh, oldw, 1), dtype=np.uint8)
 
     def observation(self, frame):
@@ -199,10 +213,8 @@ class StartDoingRandomActionsWrapper(gym.Wrapper):
                 self.some_random_steps()
         return self.last_obs, rew, done, info
 
-def make_retro(*, game, state=None, max_episode_steps=4500, **kwargs):
+def make_retro(*, game, state, max_episode_steps, **kwargs):
     import retro
-    if state is None:
-        state = retro.State.DEFAULT
     env = retro.make(game, state, **kwargs)
     env = StochasticFrameSkip(env, n=4, stickprob=0.25)
     if max_episode_steps is not None:
@@ -215,8 +227,7 @@ def wrap_deepmind_retro(env, scale=True, frame_stack=4):
     """
     env = WarpFrame(env)
     env = ClipRewardEnv(env)
-    if frame_stack > 1:
-        env = FrameStack(env, frame_stack)
+    env = FrameStack(env, frame_stack)
     if scale:
         env = ScaledFloatFrame(env)
     return env

baselines/common/running_mean_std.py

@@ -177,7 +177,7 @@ def profile_tf_runningmeanstd():
     outfile = '/tmp/timeline.json'
     with open(outfile, 'wt') as f:
         f.write(chrome_trace)
-    print('Successfully saved profile to {}. Exiting.'.format(outfile))
+    print(f'Successfully saved profile to {outfile}. Exiting.')
     exit(0)
     '''
 

baselines/common/test_mpi_util.py

@@ -1,27 +0,0 @@
-from baselines import logger
-from baselines.common.tests.test_with_mpi import with_mpi
-from baselines.common import mpi_util
-
-@with_mpi()
-def test_mpi_weighted_mean():
-    from mpi4py import MPI
-    comm = MPI.COMM_WORLD
-    with logger.scoped_configure(comm=comm):
-        if comm.rank == 0:
-            name2valcount = {'a' : (10, 2), 'b' : (20,3)}
-        elif comm.rank == 1:
-            name2valcount = {'a' : (19, 1), 'c' : (42,3)}
-        else:
-            raise NotImplementedError
-
-        d = mpi_util.mpi_weighted_mean(comm, name2valcount)
-        correctval = {'a' : (10 * 2 + 19) / 3.0, 'b' : 20, 'c' : 42}
-        if comm.rank == 0:
-            assert d == correctval, '{} != {}'.format(d, correctval)
-
-        for name, (val, count) in name2valcount.items():
-            for _ in range(count):
-                logger.logkv_mean(name, val)
-        d2 = logger.dumpkvs()
-        if comm.rank == 0:
-            assert d2 == correctval

baselines/common/tests/envs/fixed_sequence_env.py

@@ -7,20 +7,21 @@ class FixedSequenceEnv(Env):
     def __init__(
             self,
             n_actions=10,
+            seed=0,
             episode_len=100
     ):
         self.np_random = np.random.RandomState()
-        self.sequence = None
+        self.np_random.seed(seed)
+        self.sequence = [self.np_random.randint(0, n_actions-1) for _ in range(episode_len)]
 
         self.action_space = Discrete(n_actions)
         self.observation_space = Discrete(1)
 
         self.episode_len = episode_len
         self.time = 0
+        self.reset()
 
     def reset(self):
-        if self.sequence is None:
-            self.sequence = [self.np_random.randint(0, self.action_space.n-1) for _ in range(self.episode_len)]
         self.time = 0
         return 0
 
@@ -34,9 +35,6 @@ class FixedSequenceEnv(Env):
 
         return 0, rew, done, {}
 
-    def seed(self, seed=None):
-        self.np_random.seed(seed)
-
     def _choose_next_state(self):
         self.time += 1
 

baselines/common/tests/envs/identity_env.py

@@ -10,7 +10,6 @@ class IdentityEnv(Env):
             episode_len=None
     ):
 
-        self.observation_space = self.action_space
         self.episode_len = episode_len
         self.time = 0
         self.reset()
@@ -18,6 +17,7 @@ class IdentityEnv(Env):
     def reset(self):
         self._choose_next_state()
         self.time = 0
+        self.observation_space = self.action_space
 
         return self.state
 
@@ -26,13 +26,11 @@ class IdentityEnv(Env):
         self._choose_next_state()
         done = False
         if self.episode_len and self.time >= self.episode_len:
+            rew = 0
             done = True
 
         return self.state, rew, done, {}
 
-    def seed(self, seed=None):
-        self.action_space.seed(seed)
-
     def _choose_next_state(self):
         self.state = self.action_space.sample()
         self.time += 1
@@ -76,7 +74,7 @@ class BoxIdentityEnv(IdentityEnv):
             episode_len=None,
     ):
 
-        self.action_space = Box(low=-1.0, high=1.0, shape=shape, dtype=np.float32)
+        self.action_space = Box(low=-1.0, high=1.0, shape=shape)
         super().__init__(episode_len=episode_len)
 
     def _get_reward(self, actions):

baselines/common/tests/envs/mnist_env.py

@@ -9,6 +9,7 @@ from gym.spaces import Discrete, Box
 class MnistEnv(Env):
     def __init__(
             self,
+            seed=0,
             episode_len=None,
             no_images=None
     ):
@@ -22,6 +23,7 @@ class MnistEnv(Env):
            self.mnist = input_data.read_data_sets(mnist_path)
 
         self.np_random = np.random.RandomState()
+        self.np_random.seed(seed)
 
         self.observation_space = Box(low=0.0, high=1.0, shape=(28,28,1))
         self.action_space = Discrete(10)
@@ -48,9 +50,6 @@ class MnistEnv(Env):
 
         return self.state[0], rew, done, {}
 
-    def seed(self, seed=None):
-        self.np_random.seed(seed)
-
     def train_mode(self):
         self.dataset = self.mnist.train
 

baselines/common/tests/test_fetchreach.py

@@ -1,39 +0,0 @@
-import pytest
-import gym
-
-from baselines.run import get_learn_function
-from baselines.common.tests.util import reward_per_episode_test
-
-pytest.importorskip('mujoco_py')
-
-common_kwargs = dict(
-    network='mlp',
-    seed=0,
-)
-
-learn_kwargs = {
-    'her': dict(total_timesteps=2000)
-}
-
-@pytest.mark.slow
-@pytest.mark.parametrize("alg", learn_kwargs.keys())
-def test_fetchreach(alg):
-    '''
-    Test if the algorithm (with an mlp policy)
-    can learn the FetchReach task
-    '''
-
-    kwargs = common_kwargs.copy()
-    kwargs.update(learn_kwargs[alg])
-
-    learn_fn = lambda e: get_learn_function(alg)(env=e, **kwargs)
-    def env_fn():
-
-        env = gym.make('FetchReach-v1')
-        env.seed(0)
-        return env
-
-    reward_per_episode_test(env_fn, learn_fn, -15)
-
-if __name__ == '__main__':
-    test_fetchreach('her')

baselines/common/tests/test_fixed_sequence.py

@@ -17,10 +17,10 @@ learn_kwargs = {
     # 'trpo_mpi': lambda e, p: trpo_mpi.learn(policy_fn=p(env=e), env=e, max_timesteps=30000, timesteps_per_batch=100, cg_iters=10, gamma=0.9, lam=1.0, max_kl=0.001)
 }
 
+
 alg_list = learn_kwargs.keys()
 rnn_list = ['lstm']
 
-
 @pytest.mark.slow
 @pytest.mark.parametrize("alg", alg_list)
 @pytest.mark.parametrize("rnn", rnn_list)
@@ -33,10 +33,8 @@ def test_fixed_sequence(alg, rnn):
     kwargs = learn_kwargs[alg]
     kwargs.update(common_kwargs)
 
-    if alg == 'ppo2' and rnn.endswith('lstm'):
-        rnn = 'ppo_' + rnn
-
-    env_fn = lambda: FixedSequenceEnv(n_actions=10, episode_len=5)
+    episode_len = 5
+    env_fn = lambda: FixedSequenceEnv(10, episode_len=episode_len)
     learn = lambda e: get_learn_function(alg)(
         env=e,
         network=rnn,
@@ -48,3 +46,6 @@ def test_fixed_sequence(alg, rnn):
 
 if __name__ == '__main__':
     test_fixed_sequence('ppo2', 'lstm')
+
+
+

baselines/common/tests/test_mnist.py

@@ -41,7 +41,7 @@ def test_mnist(alg):
 
     learn = get_learn_function(alg)
     learn_fn = lambda e: learn(env=e, **learn_kwargs)
-    env_fn = lambda: MnistEnv(episode_len=100)
+    env_fn = lambda: MnistEnv(seed=0, episode_len=100)
 
     simple_test(env_fn, learn_fn, 0.6)
 

baselines/common/tests/test_serialization.py

@@ -1,16 +1,17 @@
 import os
-import tempfile
-from functools import partial
-
 import gym
-import numpy as np
+import tempfile
 import pytest
 import tensorflow as tf
+import numpy as np
 
 from baselines.common.tests.envs.mnist_env import MnistEnv
-from baselines.common.tf_util import make_session, get_session
 from baselines.common.vec_env.dummy_vec_env import DummyVecEnv
 from baselines.run import get_learn_function
+from baselines.common.tf_util import make_session, get_session
+
+from functools import partial
+
 
 learn_kwargs = {
     'deepq': {},
@@ -36,29 +37,22 @@ def test_serialization(learn_fn, network_fn):
     Test if the trained model can be serialized
     '''
 
-    _network_kwargs = network_kwargs[network_fn]
 
     if network_fn.endswith('lstm') and learn_fn in ['acer', 'acktr', 'trpo_mpi', 'deepq']:
-        # TODO make acktr work with recurrent policies
-        # and test
-        # github issue: https://github.com/openai/baselines/issues/660
-        return
-    elif network_fn.endswith('lstm') and learn_fn == 'ppo2':
-        network_fn = 'ppo_' + network_fn
+            # TODO make acktr work with recurrent policies
+            # and test
+            # github issue: https://github.com/openai/baselines/issues/660
+            return
 
-    def make_env():
-        env = MnistEnv(episode_len=100)
-        env.seed(10)
-        return env
-
-    env = DummyVecEnv([make_env])
+    env = DummyVecEnv([lambda: MnistEnv(10, episode_len=100)])
     ob = env.reset().copy()
     learn = get_learn_function(learn_fn)
 
     kwargs = {}
-    kwargs.update(_network_kwargs)
+    kwargs.update(network_kwargs[network_fn])
     kwargs.update(learn_kwargs[learn_fn])
 
+
     learn = partial(learn, env=env, network=network_fn, seed=0, **kwargs)
 
     with tempfile.TemporaryDirectory() as td:
@@ -77,7 +71,7 @@ def test_serialization(learn_fn, network_fn):
 
         for k, v in variables_dict1.items():
             np.testing.assert_allclose(v, variables_dict2[k], atol=0.01,
-                                       err_msg='saved and loaded variable {} value mismatch'.format(k))
+                err_msg='saved and loaded variable {} value mismatch'.format(k))
 
         np.testing.assert_allclose(mean1, mean2, atol=0.5)
         np.testing.assert_allclose(std1, std2, atol=0.5)
@@ -91,15 +85,15 @@ def test_coexistence(learn_fn, network_fn):
     '''
 
     if learn_fn == 'deepq':
-        # TODO enable multiple DQN models to be useable at the same time
-        # github issue https://github.com/openai/baselines/issues/656
-        return
+            # TODO enable multiple DQN models to be useable at the same time
+            # github issue https://github.com/openai/baselines/issues/656
+            return
 
     if network_fn.endswith('lstm') and learn_fn in ['acktr', 'trpo_mpi', 'deepq']:
-        # TODO make acktr work with recurrent policies
-        # and test
-        # github issue: https://github.com/openai/baselines/issues/660
-        return
+            # TODO make acktr work with recurrent policies
+            # and test
+            # github issue: https://github.com/openai/baselines/issues/660
+            return
 
     env = DummyVecEnv([lambda: gym.make('CartPole-v0')])
     learn = get_learn_function(learn_fn)
@@ -108,7 +102,7 @@ def test_coexistence(learn_fn, network_fn):
     kwargs.update(network_kwargs[network_fn])
     kwargs.update(learn_kwargs[learn_fn])
 
-    learn = partial(learn, env=env, network=network_fn, total_timesteps=0, **kwargs)
+    learn =  partial(learn, env=env, network=network_fn, total_timesteps=0, **kwargs)
     make_session(make_default=True, graph=tf.Graph())
     model1 = learn(seed=1)
     make_session(make_default=True, graph=tf.Graph())
@@ -118,6 +112,7 @@ def test_coexistence(learn_fn, network_fn):
     model2.step(env.observation_space.sample())
 
 
+
 def _serialize_variables():
     sess = get_session()
     variables = tf.trainable_variables()
@@ -136,3 +131,4 @@ def _get_action_stats(model, ob):
     std = np.std(actions, axis=0)
 
     return mean, std
+

baselines/common/tests/test_tf_util.py

@@ -18,9 +18,7 @@ def test_function():
             initialize()
 
             assert lin(2) == 6
-            assert lin(x=3) == 9
             assert lin(2, 2) == 10
-            assert lin(x=2, y=3) == 12
 
 
 def test_multikwargs():

baselines/common/tests/test_with_mpi.py

@@ -1,36 +0,0 @@
-import os
-import sys
-import subprocess
-import cloudpickle
-import base64
-import pytest
-
-try:
-    from mpi4py import MPI
-except ImportError:
-    MPI = None
-
-def with_mpi(nproc=2, timeout=30, skip_if_no_mpi=True):
-    def outer_thunk(fn):
-        def thunk(*args, **kwargs):
-            serialized_fn = base64.b64encode(cloudpickle.dumps(lambda: fn(*args, **kwargs)))
-            subprocess.check_call([
-                'mpiexec','-n', str(nproc),
-                sys.executable,
-                '-m', 'baselines.common.tests.test_with_mpi',
-                serialized_fn
-            ], env=os.environ, timeout=timeout)
-
-        if skip_if_no_mpi:
-            return pytest.mark.skipif(MPI is None, reason="MPI not present")(thunk)
-        else:
-            return thunk
-
-    return outer_thunk
-
-
-if __name__ == '__main__':
-    if len(sys.argv) > 1:
-        fn = cloudpickle.loads(base64.b64decode(sys.argv[1]))
-        assert callable(fn)
-        fn()

baselines/common/tests/util.py

@@ -1,44 +1,56 @@
 import tensorflow as tf
 import numpy as np
+from gym.spaces import np_random
 from baselines.common.vec_env.dummy_vec_env import DummyVecEnv
 
 N_TRIALS = 10000
 N_EPISODES = 100
 
 def simple_test(env_fn, learn_fn, min_reward_fraction, n_trials=N_TRIALS):
-    def seeded_env_fn():
-        env = env_fn()
-        env.seed(0)
-        return env
-
     np.random.seed(0)
-    env = DummyVecEnv([seeded_env_fn])
+    np_random.seed(0)
+
+    env = DummyVecEnv([env_fn])
+
+
     with tf.Graph().as_default(), tf.Session(config=tf.ConfigProto(allow_soft_placement=True)).as_default():
         tf.set_random_seed(0)
+
         model = learn_fn(env)
+
         sum_rew = 0
         done = True
+
         for i in range(n_trials):
             if done:
                 obs = env.reset()
                 state = model.initial_state
+
             if state is not None:
                 a, v, state, _ = model.step(obs, S=state, M=[False])
             else:
                 a, v, _, _ = model.step(obs)
+
             obs, rew, done, _ = env.step(a)
             sum_rew += float(rew)
+
         print("Reward in {} trials is {}".format(n_trials, sum_rew))
         assert sum_rew > min_reward_fraction * n_trials, \
             'sum of rewards {} is less than {} of the total number of trials {}'.format(sum_rew, min_reward_fraction, n_trials)
 
+
+
 def reward_per_episode_test(env_fn, learn_fn, min_avg_reward, n_trials=N_EPISODES):
     env = DummyVecEnv([env_fn])
+
     with tf.Graph().as_default(), tf.Session(config=tf.ConfigProto(allow_soft_placement=True)).as_default():
         model = learn_fn(env)
+
         N_TRIALS = 100
+
         observations, actions, rewards = rollout(env, model, N_TRIALS)
         rewards = [sum(r) for r in rewards]
+
         avg_rew = sum(rewards) / N_TRIALS
         print("Average reward in {} episodes is {}".format(n_trials, avg_rew))
         assert avg_rew > min_avg_reward, \
@@ -48,12 +60,14 @@ def rollout(env, model, n_trials):
     rewards = []
     actions = []
     observations = []
+
     for i in range(n_trials):
         obs = env.reset()
-        state = model.initial_state if hasattr(model, 'initial_state') else None
+        state = model.initial_state
         episode_rew = []
         episode_actions = []
         episode_obs = []
+
         while True:
             if state is not None:
                 a, v, state, _ = model.step(obs, S=state, M=[False])
@@ -61,13 +75,17 @@ def rollout(env, model, n_trials):
                 a,v, _, _ = model.step(obs)
 
             obs, rew, done, _ = env.step(a)
+
             episode_rew.append(rew)
             episode_actions.append(a)
             episode_obs.append(obs)
+
             if done:
                 break
+
         rewards.append(episode_rew)
         actions.append(episode_actions)
         observations.append(episode_obs)
+
     return observations, actions, rewards
 

baselines/common/tf_util.py

@@ -1,3 +1,4 @@
+import joblib
 import numpy as np
 import tensorflow as tf  # pylint: ignore-module
 import copy
@@ -185,7 +186,6 @@ class _Function(object):
             if not hasattr(inpt, 'make_feed_dict') and not (type(inpt) is tf.Tensor and len(inpt.op.inputs) == 0):
                 assert False, "inputs should all be placeholders, constants, or have a make_feed_dict method"
         self.inputs = inputs
-        self.input_names = {inp.name.split("/")[-1].split(":")[0]: inp for inp in inputs}
         updates = updates or []
         self.update_group = tf.group(*updates)
         self.outputs_update = list(outputs) + [self.update_group]
@@ -197,17 +197,15 @@ class _Function(object):
         else:
             feed_dict[inpt] = adjust_shape(inpt, value)
 
-    def __call__(self, *args, **kwargs):
-        assert len(args) + len(kwargs) <= len(self.inputs), "Too many arguments provided"
+    def __call__(self, *args):
+        assert len(args) <= len(self.inputs), "Too many arguments provided"
         feed_dict = {}
-        # Update feed dict with givens.
-        for inpt in self.givens:
-            feed_dict[inpt] = adjust_shape(inpt, feed_dict.get(inpt, self.givens[inpt]))
         # Update the args
         for inpt, value in zip(self.inputs, args):
             self._feed_input(feed_dict, inpt, value)
-        for inpt_name, value in kwargs.items():
-            self._feed_input(feed_dict, self.input_names[inpt_name], value)
+        # Update feed dict with givens.
+        for inpt in self.givens:
+            feed_dict[inpt] = adjust_shape(inpt, feed_dict.get(inpt, self.givens[inpt]))
         results = get_session().run(self.outputs_update, feed_dict=feed_dict)[:-1]
         return results
 
@@ -305,17 +303,12 @@ def display_var_info(vars):
     logger.info("Total model parameters: %0.2f million" % (count_params*1e-6))
 
 
-def get_available_gpus(session_config=None):
-    # based on recipe from https://stackoverflow.com/a/38580201
-
-    # Unless we allocate a session here, subsequent attempts to create one
-    # will ignore our custom config (in particular, allow_growth=True will have
-    # no effect).
-    if session_config is None:
-        session_config = get_session()._config
+def get_available_gpus():
+    # recipe from here:
+    # https://stackoverflow.com/questions/38559755/how-to-get-current-available-gpus-in-tensorflow?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa
 
     from tensorflow.python.client import device_lib
-    local_device_protos = device_lib.list_local_devices(session_config)
+    local_device_protos = device_lib.list_local_devices()
     return [x.name for x in local_device_protos if x.device_type == 'GPU']
 
 # ================================================================
@@ -343,9 +336,8 @@ def save_state(fname, sess=None):
 # TODO: ensure there is no subtle differences and remove one
 
 def save_variables(save_path, variables=None, sess=None):
-    import joblib
     sess = sess or get_session()
-    variables = variables or tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
+    variables = variables or tf.trainable_variables()
 
     ps = sess.run(variables)
     save_dict = {v.name: value for v, value in zip(variables, ps)}
@@ -355,9 +347,8 @@ def save_variables(save_path, variables=None, sess=None):
     joblib.dump(save_dict, save_path)
 
 def load_variables(load_path, variables=None, sess=None):
-    import joblib
     sess = sess or get_session()
-    variables = variables or tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
+    variables = variables or tf.trainable_variables()
 
     loaded_params = joblib.load(os.path.expanduser(load_path))
     restores = []

baselines/common/vec_env/__init__.py

@@ -1,10 +1,185 @@
-from .vec_env import AlreadySteppingError, NotSteppingError, VecEnv, VecEnvWrapper, VecEnvObservationWrapper, CloudpickleWrapper
-from .dummy_vec_env import DummyVecEnv
-from .shmem_vec_env import ShmemVecEnv
-from .subproc_vec_env import SubprocVecEnv
-from .vec_frame_stack import VecFrameStack
-from .vec_monitor import VecMonitor
-from .vec_normalize import VecNormalize
-from .vec_remove_dict_obs import VecExtractDictObs
+from abc import ABC, abstractmethod
+from baselines.common.tile_images import tile_images
 
-__all__ = ['AlreadySteppingError', 'NotSteppingError', 'VecEnv', 'VecEnvWrapper', 'VecEnvObservationWrapper', 'CloudpickleWrapper', 'DummyVecEnv', 'ShmemVecEnv', 'SubprocVecEnv', 'VecFrameStack', 'VecMonitor', 'VecNormalize', 'VecExtractDictObs']
+class AlreadySteppingError(Exception):
+    """
+    Raised when an asynchronous step is running while
+    step_async() is called again.
+    """
+
+    def __init__(self):
+        msg = 'already running an async step'
+        Exception.__init__(self, msg)
+
+
+class NotSteppingError(Exception):
+    """
+    Raised when an asynchronous step is not running but
+    step_wait() is called.
+    """
+
+    def __init__(self):
+        msg = 'not running an async step'
+        Exception.__init__(self, msg)
+
+
+class VecEnv(ABC):
+    """
+    An abstract asynchronous, vectorized environment.
+    Used to batch data from multiple copies of an environment, so that
+    each observation becomes an batch of observations, and expected action is a batch of actions to
+    be applied per-environment.
+    """
+    closed = False
+    viewer = None
+
+    metadata = {
+        'render.modes': ['human', 'rgb_array']
+    }
+
+    def __init__(self, num_envs, observation_space, action_space):
+        self.num_envs = num_envs
+        self.observation_space = observation_space
+        self.action_space = action_space
+
+    @abstractmethod
+    def reset(self):
+        """
+        Reset all the environments and return an array of
+        observations, or a dict of observation arrays.
+
+        If step_async is still doing work, that work will
+        be cancelled and step_wait() should not be called
+        until step_async() is invoked again.
+        """
+        pass
+
+    @abstractmethod
+    def step_async(self, actions):
+        """
+        Tell all the environments to start taking a step
+        with the given actions.
+        Call step_wait() to get the results of the step.
+
+        You should not call this if a step_async run is
+        already pending.
+        """
+        pass
+
+    @abstractmethod
+    def step_wait(self):
+        """
+        Wait for the step taken with step_async().
+
+        Returns (obs, rews, dones, infos):
+         - obs: an array of observations, or a dict of
+                arrays of observations.
+         - rews: an array of rewards
+         - dones: an array of "episode done" booleans
+         - infos: a sequence of info objects
+        """
+        pass
+
+    def close_extras(self):
+        """
+        Clean up the  extra resources, beyond what's in this base class.
+        Only runs when not self.closed.
+        """
+        pass
+
+    def close(self):
+        if self.closed:
+            return
+        if self.viewer is not None:
+            self.viewer.close()
+        self.close_extras()
+        self.closed = True
+
+    def step(self, actions):
+        """
+        Step the environments synchronously.
+
+        This is available for backwards compatibility.
+        """
+        self.step_async(actions)
+        return self.step_wait()
+
+    def render(self, mode='human'):
+        imgs = self.get_images()
+        bigimg = tile_images(imgs)
+        if mode == 'human':
+            self.get_viewer().imshow(bigimg)
+            return self.get_viewer().isopen
+        elif mode == 'rgb_array':
+            return bigimg
+        else:
+            raise NotImplementedError
+
+    def get_images(self):
+        """
+        Return RGB images from each environment
+        """
+        raise NotImplementedError
+
+    @property
+    def unwrapped(self):
+        if isinstance(self, VecEnvWrapper):
+            return self.venv.unwrapped
+        else:
+            return self
+
+    def get_viewer(self):
+        if self.viewer is None:
+            from gym.envs.classic_control import rendering
+            self.viewer = rendering.SimpleImageViewer()
+        return self.viewer
+
+
+class VecEnvWrapper(VecEnv):
+    """
+    An environment wrapper that applies to an entire batch
+    of environments at once.
+    """
+
+    def __init__(self, venv, observation_space=None, action_space=None):
+        self.venv = venv
+        VecEnv.__init__(self,
+                        num_envs=venv.num_envs,
+                        observation_space=observation_space or venv.observation_space,
+                        action_space=action_space or venv.action_space)
+
+    def step_async(self, actions):
+        self.venv.step_async(actions)
+
+    @abstractmethod
+    def reset(self):
+        pass
+
+    @abstractmethod
+    def step_wait(self):
+        pass
+
+    def close(self):
+        return self.venv.close()
+
+    def render(self, mode='human'):
+        return self.venv.render(mode=mode)
+
+    def get_images(self):
+        return self.venv.get_images()
+
+class CloudpickleWrapper(object):
+    """
+    Uses cloudpickle to serialize contents (otherwise multiprocessing tries to use pickle)
+    """
+
+    def __init__(self, x):
+        self.x = x
+
+    def __getstate__(self):
+        import cloudpickle
+        return cloudpickle.dumps(self.x)
+
+    def __setstate__(self, ob):
+        import pickle
+        self.x = pickle.loads(ob)

baselines/common/vec_env/dummy_vec_env.py

@@ -1,5 +1,6 @@
 import numpy as np
-from .vec_env import VecEnv
+from gym import spaces
+from . import VecEnv
 from .util import copy_obs_dict, dict_to_obs, obs_space_info
 
 class DummyVecEnv(VecEnv):
@@ -26,7 +27,6 @@ class DummyVecEnv(VecEnv):
         self.buf_rews  = np.zeros((self.num_envs,), dtype=np.float32)
         self.buf_infos = [{} for _ in range(self.num_envs)]
         self.actions = None
-        self.spec = self.envs[0].spec
 
     def step_async(self, actions):
         listify = True
@@ -45,8 +45,8 @@ class DummyVecEnv(VecEnv):
     def step_wait(self):
         for e in range(self.num_envs):
             action = self.actions[e]
-            # if isinstance(self.envs[e].action_space, spaces.Discrete):
-            #    action = int(action)
+            if isinstance(self.envs[e].action_space, spaces.Discrete):
+                action = int(action)
 
             obs, self.buf_rews[e], self.buf_dones[e], self.buf_infos[e] = self.envs[e].step(action)
             if self.buf_dones[e]:

baselines/common/vec_env/shmem_vec_env.py

@@ -2,9 +2,9 @@
 An interface for asynchronous vectorized environments.
 """
 
-import multiprocessing as mp
+from multiprocessing import Pipe, Array, Process
 import numpy as np
-from .vec_env import VecEnv, CloudpickleWrapper, clear_mpi_env_vars
+from . import VecEnv, CloudpickleWrapper
 import ctypes
 from baselines import logger
 
@@ -22,12 +22,11 @@ class ShmemVecEnv(VecEnv):
     Optimized version of SubprocVecEnv that uses shared variables to communicate observations.
     """
 
-    def __init__(self, env_fns, spaces=None, context='spawn'):
+    def __init__(self, env_fns, spaces=None):
         """
         If you don't specify observation_space, we'll have to create a dummy
         environment to get it.
         """
-        ctx = mp.get_context(context)
         if spaces:
             observation_space, action_space = spaces
         else:
@@ -40,21 +39,20 @@ class ShmemVecEnv(VecEnv):
         VecEnv.__init__(self, len(env_fns), observation_space, action_space)
         self.obs_keys, self.obs_shapes, self.obs_dtypes = obs_space_info(observation_space)
         self.obs_bufs = [
-            {k: ctx.Array(_NP_TO_CT[self.obs_dtypes[k].type], int(np.prod(self.obs_shapes[k]))) for k in self.obs_keys}
+            {k: Array(_NP_TO_CT[self.obs_dtypes[k].type], int(np.prod(self.obs_shapes[k]))) for k in self.obs_keys}
             for _ in env_fns]
         self.parent_pipes = []
         self.procs = []
-        with clear_mpi_env_vars():
-            for env_fn, obs_buf in zip(env_fns, self.obs_bufs):
-                wrapped_fn = CloudpickleWrapper(env_fn)
-                parent_pipe, child_pipe = ctx.Pipe()
-                proc = ctx.Process(target=_subproc_worker,
-                            args=(child_pipe, parent_pipe, wrapped_fn, obs_buf, self.obs_shapes, self.obs_dtypes, self.obs_keys))
-                proc.daemon = True
-                self.procs.append(proc)
-                self.parent_pipes.append(parent_pipe)
-                proc.start()
-                child_pipe.close()
+        for env_fn, obs_buf in zip(env_fns, self.obs_bufs):
+            wrapped_fn = CloudpickleWrapper(env_fn)
+            parent_pipe, child_pipe = Pipe()
+            proc = Process(target=_subproc_worker,
+                           args=(child_pipe, parent_pipe, wrapped_fn, obs_buf, self.obs_shapes, self.obs_dtypes, self.obs_keys))
+            proc.daemon = True
+            self.procs.append(proc)
+            self.parent_pipes.append(parent_pipe)
+            proc.start()
+            child_pipe.close()
         self.waiting_step = False
         self.viewer = None
 

baselines/common/vec_env/subproc_vec_env.py

@@ -1,8 +1,6 @@
-import multiprocessing as mp
-
 import numpy as np
-from .vec_env import VecEnv, CloudpickleWrapper, clear_mpi_env_vars
-
+from multiprocessing import Process, Pipe
+from . import VecEnv, CloudpickleWrapper
 
 def worker(remote, parent_remote, env_fn_wrapper):
     parent_remote.close()
@@ -23,8 +21,8 @@ def worker(remote, parent_remote, env_fn_wrapper):
             elif cmd == 'close':
                 remote.close()
                 break
-            elif cmd == 'get_spaces_spec':
-                remote.send((env.observation_space, env.action_space, env.spec))
+            elif cmd == 'get_spaces':
+                remote.send((env.observation_space, env.action_space))
             else:
                 raise NotImplementedError
     except KeyboardInterrupt:
@@ -38,7 +36,7 @@ class SubprocVecEnv(VecEnv):
     VecEnv that runs multiple environments in parallel in subproceses and communicates with them via pipes.
     Recommended to use when num_envs > 1 and step() can be a bottleneck.
     """
-    def __init__(self, env_fns, spaces=None, context='spawn'):
+    def __init__(self, env_fns, spaces=None):
         """
         Arguments:
 
@@ -47,19 +45,17 @@ class SubprocVecEnv(VecEnv):
         self.waiting = False
         self.closed = False
         nenvs = len(env_fns)
-        ctx = mp.get_context(context)
-        self.remotes, self.work_remotes = zip(*[ctx.Pipe() for _ in range(nenvs)])
-        self.ps = [ctx.Process(target=worker, args=(work_remote, remote, CloudpickleWrapper(env_fn)))
+        self.remotes, self.work_remotes = zip(*[Pipe() for _ in range(nenvs)])
+        self.ps = [Process(target=worker, args=(work_remote, remote, CloudpickleWrapper(env_fn)))
                    for (work_remote, remote, env_fn) in zip(self.work_remotes, self.remotes, env_fns)]
         for p in self.ps:
             p.daemon = True  # if the main process crashes, we should not cause things to hang
-            with clear_mpi_env_vars():
-                p.start()
+            p.start()
         for remote in self.work_remotes:
             remote.close()
 
-        self.remotes[0].send(('get_spaces_spec', None))
-        observation_space, action_space, self.spec = self.remotes[0].recv()
+        self.remotes[0].send(('get_spaces', None))
+        observation_space, action_space = self.remotes[0].recv()
         self.viewer = None
         VecEnv.__init__(self, len(env_fns), observation_space, action_space)
 
@@ -74,13 +70,13 @@ class SubprocVecEnv(VecEnv):
         results = [remote.recv() for remote in self.remotes]
         self.waiting = False
         obs, rews, dones, infos = zip(*results)
-        return _flatten_obs(obs), np.stack(rews), np.stack(dones), infos
+        return np.stack(obs), np.stack(rews), np.stack(dones), infos
 
     def reset(self):
         self._assert_not_closed()
         for remote in self.remotes:
             remote.send(('reset', None))
-        return _flatten_obs([remote.recv() for remote in self.remotes])
+        return np.stack([remote.recv() for remote in self.remotes])
 
     def close_extras(self):
         self.closed = True
@@ -101,17 +97,3 @@ class SubprocVecEnv(VecEnv):
 
     def _assert_not_closed(self):
         assert not self.closed, "Trying to operate on a SubprocVecEnv after calling close()"
-
-    def __del__(self):
-        if not self.closed:
-            self.close()
-
-def _flatten_obs(obs):
-    assert isinstance(obs, (list, tuple))
-    assert len(obs) > 0
-
-    if isinstance(obs[0], dict):
-        keys = obs[0].keys()
-        return {k: np.stack([o[k] for o in obs]) for k in keys}
-    else:
-        return np.stack(obs)

baselines/common/vec_env/test_vec_env.py

@@ -8,40 +8,39 @@ import pytest
 from .dummy_vec_env import DummyVecEnv
 from .shmem_vec_env import ShmemVecEnv
 from .subproc_vec_env import SubprocVecEnv
-from baselines.common.tests.test_with_mpi import with_mpi
 
 
-def assert_venvs_equal(venv1, venv2, num_steps):
+def assert_envs_equal(env1, env2, num_steps):
     """
     Compare two environments over num_steps steps and make sure
     that the observations produced by each are the same when given
     the same actions.
     """
-    assert venv1.num_envs == venv2.num_envs
-    assert venv1.observation_space.shape == venv2.observation_space.shape
-    assert venv1.observation_space.dtype == venv2.observation_space.dtype
-    assert venv1.action_space.shape == venv2.action_space.shape
-    assert venv1.action_space.dtype == venv2.action_space.dtype
+    assert env1.num_envs == env2.num_envs
+    assert env1.action_space.shape == env2.action_space.shape
+    assert env1.action_space.dtype == env2.action_space.dtype
+    joint_shape = (env1.num_envs,) + env1.action_space.shape
 
     try:
-        obs1, obs2 = venv1.reset(), venv2.reset()
+        obs1, obs2 = env1.reset(), env2.reset()
         assert np.array(obs1).shape == np.array(obs2).shape
-        assert np.array(obs1).shape == (venv1.num_envs,) + venv1.observation_space.shape
+        assert np.array(obs1).shape == joint_shape
         assert np.allclose(obs1, obs2)
-        venv1.action_space.seed(1337)
+        np.random.seed(1337)
         for _ in range(num_steps):
-            actions = np.array([venv1.action_space.sample() for _ in range(venv1.num_envs)])
-            for venv in [venv1, venv2]:
-                venv.step_async(actions)
-            outs1 = venv1.step_wait()
-            outs2 = venv2.step_wait()
+            actions = np.array(np.random.randint(0, 0x100, size=joint_shape),
+                               dtype=env1.action_space.dtype)
+            for env in [env1, env2]:
+                env.step_async(actions)
+            outs1 = env1.step_wait()
+            outs2 = env2.step_wait()
             for out1, out2 in zip(outs1[:3], outs2[:3]):
                 assert np.array(out1).shape == np.array(out2).shape
                 assert np.allclose(out1, out2)
             assert list(outs1[3]) == list(outs2[3])
     finally:
-        venv1.close()
-        venv2.close()
+        env1.close()
+        env2.close()
 
 
 @pytest.mark.parametrize('klass', (ShmemVecEnv, SubprocVecEnv))
@@ -64,7 +63,7 @@ def test_vec_env(klass, dtype):  # pylint: disable=R0914
     fns = [make_fn(i) for i in range(num_envs)]
     env1 = DummyVecEnv(fns)
     env2 = klass(fns)
-    assert_venvs_equal(env1, env2, num_steps=num_steps)
+    assert_envs_equal(env1, env2, num_steps=num_steps)
 
 
 class SimpleEnv(gym.Env):
@@ -100,15 +99,3 @@ class SimpleEnv(gym.Env):
 
     def render(self, mode=None):
         raise NotImplementedError
-
-
-
-@with_mpi()
-def test_mpi_with_subprocvecenv():
-    shape = (2,3,4)
-    nenv = 1
-    venv = SubprocVecEnv([lambda: SimpleEnv(0, shape, 'float32')] * nenv)
-    ob = venv.reset()
-    venv.close()
-    assert ob.shape == (nenv,) + shape
-

baselines/common/vec_env/vec_env.py

@@ -1,219 +0,0 @@
-import contextlib
-import os
-from abc import ABC, abstractmethod
-
-from baselines.common.tile_images import tile_images
-
-class AlreadySteppingError(Exception):
-    """
-    Raised when an asynchronous step is running while
-    step_async() is called again.
-    """
-
-    def __init__(self):
-        msg = 'already running an async step'
-        Exception.__init__(self, msg)
-
-
-class NotSteppingError(Exception):
-    """
-    Raised when an asynchronous step is not running but
-    step_wait() is called.
-    """
-
-    def __init__(self):
-        msg = 'not running an async step'
-        Exception.__init__(self, msg)
-
-
-class VecEnv(ABC):
-    """
-    An abstract asynchronous, vectorized environment.
-    Used to batch data from multiple copies of an environment, so that
-    each observation becomes an batch of observations, and expected action is a batch of actions to
-    be applied per-environment.
-    """
-    closed = False
-    viewer = None
-
-    metadata = {
-        'render.modes': ['human', 'rgb_array']
-    }
-
-    def __init__(self, num_envs, observation_space, action_space):
-        self.num_envs = num_envs
-        self.observation_space = observation_space
-        self.action_space = action_space
-
-    @abstractmethod
-    def reset(self):
-        """
-        Reset all the environments and return an array of
-        observations, or a dict of observation arrays.
-
-        If step_async is still doing work, that work will
-        be cancelled and step_wait() should not be called
-        until step_async() is invoked again.
-        """
-        pass
-
-    @abstractmethod
-    def step_async(self, actions):
-        """
-        Tell all the environments to start taking a step
-        with the given actions.
-        Call step_wait() to get the results of the step.
-
-        You should not call this if a step_async run is
-        already pending.
-        """
-        pass
-
-    @abstractmethod
-    def step_wait(self):
-        """
-        Wait for the step taken with step_async().
-
-        Returns (obs, rews, dones, infos):
-         - obs: an array of observations, or a dict of
-                arrays of observations.
-         - rews: an array of rewards
-         - dones: an array of "episode done" booleans
-         - infos: a sequence of info objects
-        """
-        pass
-
-    def close_extras(self):
-        """
-        Clean up the  extra resources, beyond what's in this base class.
-        Only runs when not self.closed.
-        """
-        pass
-
-    def close(self):
-        if self.closed:
-            return
-        if self.viewer is not None:
-            self.viewer.close()
-        self.close_extras()
-        self.closed = True
-
-    def step(self, actions):
-        """
-        Step the environments synchronously.
-
-        This is available for backwards compatibility.
-        """
-        self.step_async(actions)
-        return self.step_wait()
-
-    def render(self, mode='human'):
-        imgs = self.get_images()
-        bigimg = tile_images(imgs)
-        if mode == 'human':
-            self.get_viewer().imshow(bigimg)
-            return self.get_viewer().isopen
-        elif mode == 'rgb_array':
-            return bigimg
-        else:
-            raise NotImplementedError
-
-    def get_images(self):
-        """
-        Return RGB images from each environment
-        """
-        raise NotImplementedError
-
-    @property
-    def unwrapped(self):
-        if isinstance(self, VecEnvWrapper):
-            return self.venv.unwrapped
-        else:
-            return self
-
-    def get_viewer(self):
-        if self.viewer is None:
-            from gym.envs.classic_control import rendering
-            self.viewer = rendering.SimpleImageViewer()
-        return self.viewer
-
-class VecEnvWrapper(VecEnv):
-    """
-    An environment wrapper that applies to an entire batch
-    of environments at once.
-    """
-
-    def __init__(self, venv, observation_space=None, action_space=None):
-        self.venv = venv
-        VecEnv.__init__(self,
-                        num_envs=venv.num_envs,
-                        observation_space=observation_space or venv.observation_space,
-                        action_space=action_space or venv.action_space)
-
-    def step_async(self, actions):
-        self.venv.step_async(actions)
-
-    @abstractmethod
-    def reset(self):
-        pass
-
-    @abstractmethod
-    def step_wait(self):
-        pass
-
-    def close(self):
-        return self.venv.close()
-
-    def render(self, mode='human'):
-        return self.venv.render(mode=mode)
-
-    def get_images(self):
-        return self.venv.get_images()
-
-class VecEnvObservationWrapper(VecEnvWrapper):
-    @abstractmethod
-    def process(self, obs):
-        pass
-
-    def reset(self):
-        obs = self.venv.reset()
-        return self.process(obs)
-
-    def step_wait(self):
-        obs, rews, dones, infos = self.venv.step_wait()
-        return self.process(obs), rews, dones, infos
-
-class CloudpickleWrapper(object):
-    """
-    Uses cloudpickle to serialize contents (otherwise multiprocessing tries to use pickle)
-    """
-
-    def __init__(self, x):
-        self.x = x
-
-    def __getstate__(self):
-        import cloudpickle
-        return cloudpickle.dumps(self.x)
-
-    def __setstate__(self, ob):
-        import pickle
-        self.x = pickle.loads(ob)
-
-
-@contextlib.contextmanager
-def clear_mpi_env_vars():
-    """
-    from mpi4py import MPI will call MPI_Init by default.  If the child process has MPI environment variables, MPI will think that the child process is an MPI process just like the parent and do bad things such as hang.
-    This context manager is a hacky way to clear those environment variables temporarily such as when we are starting multiprocessing
-    Processes.
-    """
-    removed_environment = {}
-    for k, v in list(os.environ.items()):
-        for prefix in ['OMPI_', 'PMI_']:
-            if k.startswith(prefix):
-                removed_environment[k] = v
-                del os.environ[k]
-    try:
-        yield
-    finally:
-        os.environ.update(removed_environment)

baselines/common/vec_env/vec_frame_stack.py

@@ -1,4 +1,4 @@
-from .vec_env import VecEnvWrapper
+from . import VecEnvWrapper
 import numpy as np
 from gym import spaces
 

baselines/common/vec_env/vec_monitor.py

@@ -2,23 +2,15 @@ from . import VecEnvWrapper
 from baselines.bench.monitor import ResultsWriter
 import numpy as np
 import time
-from collections import deque
+
 
 class VecMonitor(VecEnvWrapper):
-    def __init__(self, venv, filename=None, keep_buf=0):
+    def __init__(self, venv, filename=None):
         VecEnvWrapper.__init__(self, venv)
         self.eprets = None
         self.eplens = None
-        self.epcount = 0
         self.tstart = time.time()
-        if filename:
-            self.results_writer = ResultsWriter(filename, header={'t_start': self.tstart})
-        else:
-            self.results_writer = None
-        self.keep_buf = keep_buf
-        if self.keep_buf:
-            self.epret_buf = deque([], maxlen=keep_buf)
-            self.eplen_buf = deque([], maxlen=keep_buf)
+        self.results_writer = ResultsWriter(filename, header={'t_start': self.tstart})
 
     def reset(self):
         obs = self.venv.reset()
@@ -36,14 +28,10 @@ class VecMonitor(VecEnvWrapper):
             if done:
                 epinfo = {'r': ret, 'l': eplen, 't': round(time.time() - self.tstart, 6)}
                 info['episode'] = epinfo
-                if self.keep_buf:
-                    self.epret_buf.append(ret)
-                    self.eplen_buf.append(eplen)
-                self.epcount += 1
                 self.eprets[i] = 0
                 self.eplens[i] = 0
-                if self.results_writer:
-                    self.results_writer.write_row(epinfo)
+                self.results_writer.write_row(epinfo)
+
             newinfos.append(info)
 
         return obs, rews, dones, newinfos

baselines/common/vec_env/vec_remove_dict_obs.py

@@ -1,11 +0,0 @@
-from .vec_env import VecEnvObservationWrapper
-
-
-class VecExtractDictObs(VecEnvObservationWrapper):
-    def __init__(self, venv, key):
-        self.key = key
-        super().__init__(venv=venv,
-            observation_space=venv.observation_space.spaces[self.key])
-
-    def process(self, obs):
-        return obs[self.key]

baselines/common/wrappers.py

@@ -1,19 +0,0 @@
-import gym
-
-class TimeLimit(gym.Wrapper):
-    def __init__(self, env, max_episode_steps=None):
-        super(TimeLimit, self).__init__(env)
-        self._max_episode_steps = max_episode_steps
-        self._elapsed_steps = 0
-
-    def step(self, ac):
-        observation, reward, done, info = self.env.step(ac)
-        self._elapsed_steps += 1
-        if self._elapsed_steps >= self._max_episode_steps:
-            done = True
-            info['TimeLimit.truncated'] = True
-        return observation, reward, done, info
-
-    def reset(self, **kwargs):
-        self._elapsed_steps = 0
-        return self.env.reset(**kwargs)

baselines/ddpg/ddpg_learner.py

@@ -17,7 +17,7 @@ except ImportError:
 def normalize(x, stats):
     if stats is None:
         return x
-    return (x - stats.mean) / (stats.std + 1e-8)
+    return (x - stats.mean) / stats.std
 
 
 def denormalize(x, stats):

baselines/ddpg/test_smoke.py

@@ -1,10 +1,7 @@
-from multiprocessing import Process
-import baselines.run
+from baselines.run import main as M
 
 def _run(argstr):
-    p = Process(target=baselines.run.main, args=('--alg=ddpg --env=Pendulum-v0 --num_timesteps=0 ' + argstr).split(' '))
-    p.start()
-    p.join()
+    M(('--alg=ddpg --env=Pendulum-v0 --num_timesteps=0 ' + argstr).split(' '))
 
 def test_popart():
     _run('--normalize_returns=True --popart=True')

baselines/deepq/experiments/custom_cartpole.py

@@ -23,7 +23,7 @@ def model(inpt, num_actions, scope, reuse=False):
 
 
 if __name__ == '__main__':
-    with U.make_session(num_cpu=8):
+    with U.make_session(8):
         # Create the environment
         env = gym.make("CartPole-v0")
         # Create all the functions necessary to train the model

baselines/deepq/utils.py

@@ -20,7 +20,7 @@ class TfInput(object):
         """
         raise NotImplementedError
 
-    def make_feed_dict(self, data):
+    def make_feed_dict(data):
         """Given data input it to the placeholder(s)."""
         raise NotImplementedError
 

baselines/gail/README.md

@@ -12,13 +12,13 @@ Download the expert data into `./data`, [download link](https://drive.google.com
 
 ### Step 2: Run GAIL
 
-Run with single rank:
+Run with single thread:
 
 ```bash
 python -m baselines.gail.run_mujoco
 ```
 
-Run with multiple ranks:
+Run with multiple threads:
 
 ```bash
 mpirun -np 16 python -m baselines.gail.run_mujoco

baselines/gail/adversary.py

@@ -66,7 +66,7 @@ class TransitionClassifier(object):
 
             with tf.variable_scope("obfilter"):
                 self.obs_rms = RunningMeanStd(shape=self.observation_shape)
-            obs = (obs_ph - self.obs_rms.mean) / self.obs_rms.std
+            obs = (obs_ph - self.obs_rms.mean / self.obs_rms.std)
             _input = tf.concat([obs, acs_ph], axis=1)  # concatenate the two input -> form a transition
             p_h1 = tf.contrib.layers.fully_connected(_input, self.hidden_size, activation_fn=tf.nn.tanh)
             p_h2 = tf.contrib.layers.fully_connected(p_h1, self.hidden_size, activation_fn=tf.nn.tanh)

baselines/gail/dataset/mujoco_dset.py

@@ -50,12 +50,8 @@ class Mujoco_Dset(object):
         # obs, acs: shape (N, L, ) + S where N = # episodes, L = episode length
         # and S is the environment observation/action space.
         # Flatten to (N * L, prod(S))
-        if len(obs.shape) > 2:
-            self.obs = np.reshape(obs, [-1, np.prod(obs.shape[2:])])
-            self.acs = np.reshape(acs, [-1, np.prod(acs.shape[2:])])
-        else:
-            self.obs = np.vstack(obs)
-            self.acs = np.vstack(acs)
+        self.obs = np.reshape(obs, [-1, np.prod(obs.shape[2:])])
+        self.acs = np.reshape(acs, [-1, np.prod(acs.shape[2:])])
 
         self.rets = traj_data['ep_rets'][:traj_limitation]
         self.avg_ret = sum(self.rets)/len(self.rets)

baselines/gail/result/gail-result.md

@@ -24,7 +24,7 @@ Hopper-v1, Walker2d-v1, HalfCheetah-v1, Humanoid-v1, HumanoidStandup-v1. Every i
 
 For details (e.g., adversarial loss, discriminator accuracy, etc.) about GAIL training, please see [here](https://drive.google.com/drive/folders/1nnU8dqAV9i37-_5_vWIspyFUJFQLCsDD?usp=sharing)
 
-### Determinstic Policy (Set std=0)
+### Determinstic Polciy (Set std=0)
 |   | Un-normalized | Normalized |
 |---|---|---|
 | Hopper-v1 | <img src='Hopper-unnormalized-deterministic-scores.png'> | <img src='Hopper-normalized-deterministic-scores.png'> |

baselines/her/README.md

@@ -6,29 +6,26 @@ For details on Hindsight Experience Replay (HER), please read the [paper](https:
 ### Getting started
 Training an agent is very simple:
 ```bash
-python -m baselines.run --alg=her --env=FetchReach-v1 --num_timesteps=5000
+python -m baselines.her.experiment.train
 ```
 This will train a DDPG+HER agent on the `FetchReach` environment.
 You should see the success rate go up quickly to `1.0`, which means that the agent achieves the
-desired goal in 100% of the cases (note how HER can solve it in <5k steps - try doing that with PPO by replacing her with ppo2 :))
-The training script logs other diagnostics as well. Policy at the end of the training can be saved using `--save_path` flag, for instance:
-```bash
-python -m baselines.run --alg=her --env=FetchReach-v1 --num_timesteps=5000 --save_path=~/policies/her/fetchreach5k
-```
+desired goal in 100% of the cases.
+The training script logs other diagnostics as well and pickles the best policy so far (w.r.t. to its test success rate),
+the latest policy, and, if enabled, a history of policies every K epochs.
 
-To inspect what the agent has learned, use the `--play` flag: 
+To inspect what the agent has learned, use the play script:
 ```bash
-python -m baselines.run --alg=her --env=FetchReach-v1 --num_timesteps=5000 --play
+python -m baselines.her.experiment.play /path/to/an/experiment/policy_best.pkl
 ```
-(note `--play` can be combined with `--load_path`, which lets one load trained policies, for more results see [README.md](../../README.md))
+You can try it right now with the results of the training step (the script prints out the path for you).
+This should visualize the current policy for 10 episodes and will also print statistics.
 
 
 ### Reproducing results
-In [Plappert et al. (2018)](https://arxiv.org/abs/1802.09464), 38 trajectories were generated in parallel
-(19 MPI processes, each generating computing gradients from 2 trajectories and aggregating). 
-To reproduce that behaviour, use 
+In order to reproduce the results from [Plappert et al. (2018)](https://arxiv.org/abs/1802.09464), run the following command:
 ```bash
-mpirun -np 19 python -m baselines.run --num_env=2 --alg=her ... 
+python -m baselines.her.experiment.train --num_cpu 19
 ```
 This will require a machine with sufficient amount of physical CPU cores. In our experiments,
 we used [Azure's D15v2 instances](https://docs.microsoft.com/en-us/azure/virtual-machines/linux/sizes),
@@ -48,13 +45,6 @@ python experiment/data_generation/fetch_data_generation.py
 ```
 This outputs ```data_fetch_random_100.npz``` file which is our data file.
 
-To launch training with demonstrations (more technically, with behaviour cloning loss as an auxilliary loss), run the following
-```bash
-python -m baselines.run --alg=her --env=FetchPickAndPlace-v1 --num_timesteps=2.5e6 --demo_file=/Path/to/demo_file.npz
-```
-This will train a DDPG+HER agent on the `FetchPickAndPlace` environment by using previously generated demonstration data.
-To inspect what the agent has learned, use the `--play` flag as described above.
-
 #### Configuration
 The provided configuration is for training an agent with HER without demonstrations, we need to change a few paramters for the HER algorithm to learn through demonstrations, to do that, set:
 
@@ -72,7 +62,13 @@ Apart from these changes the reported results also have the following configurat
 * random_eps: 0.1  - percentage of time a random action is taken
 * noise_eps: 0.1  - std of gaussian noise added to not-completely-random actions
 
-These parameters can be changed either in [experiment/config.py](experiment/config.py) or passed to the command line as `--param=value`)
+Now training an agent with pre-recorded demonstrations:
+```bash
+python -m baselines.her.experiment.train --env=FetchPickAndPlace-v0 --n_epochs=1000 --demo_file=/Path/to/demo_file.npz --num_cpu=1
+```
+
+This will train a DDPG+HER agent on the `FetchPickAndPlace` environment by using previously generated demonstration data.
+To inspect what the agent has learned, use the play script as described above.
 
 ### Results
 Training with demonstrations helps overcome the exploration problem and achieves a faster and better convergence. The following graphs contrast the difference between training with and without demonstration data, We report the mean Q values vs Epoch and the Success Rate vs Epoch:
@@ -82,4 +78,3 @@ Training with demonstrations helps overcome the exploration problem and achieves
 <center><img src="../../data/fetchPickAndPlaceContrast.png"></center>
 <div class="thecap" align="middle"><b>Training results for Fetch Pick and Place task constrasting between training with and without demonstration data.</b></div>
 </div>
-

baselines/her/ddpg.py

@@ -10,14 +10,13 @@ from baselines.her.util import (
 from baselines.her.normalizer import Normalizer
 from baselines.her.replay_buffer import ReplayBuffer
 from baselines.common.mpi_adam import MpiAdam
-from baselines.common import tf_util
 
 
 def dims_to_shapes(input_dims):
     return {key: tuple([val]) if val > 0 else tuple() for key, val in input_dims.items()}
 
 
-global DEMO_BUFFER #buffer for demonstrations
+global demoBuffer #buffer for demonstrations
 
 class DDPG(object):
     @store_args
@@ -95,16 +94,16 @@ class DDPG(object):
             self._create_network(reuse=reuse)
 
         # Configure the replay buffer.
-        buffer_shapes = {key: (self.T-1 if key != 'o' else self.T, *input_shapes[key])
+        buffer_shapes = {key: (self.T if key != 'o' else self.T+1, *input_shapes[key])
                          for key, val in input_shapes.items()}
         buffer_shapes['g'] = (buffer_shapes['g'][0], self.dimg)
-        buffer_shapes['ag'] = (self.T, self.dimg)
+        buffer_shapes['ag'] = (self.T+1, self.dimg)
 
         buffer_size = (self.buffer_size // self.rollout_batch_size) * self.rollout_batch_size
         self.buffer = ReplayBuffer(buffer_shapes, buffer_size, self.T, self.sample_transitions)
 
-        global DEMO_BUFFER
-        DEMO_BUFFER = ReplayBuffer(buffer_shapes, buffer_size, self.T, self.sample_transitions) #initialize the demo buffer; in the same way as the primary data buffer
+        global demoBuffer
+        demoBuffer = ReplayBuffer(buffer_shapes, buffer_size, self.T, self.sample_transitions) #initialize the demo buffer; in the same way as the primary data buffer
 
     def _random_action(self, n):
         return np.random.uniform(low=-self.max_u, high=self.max_u, size=(n, self.dimu))
@@ -120,11 +119,6 @@ class DDPG(object):
         g = np.clip(g, -self.clip_obs, self.clip_obs)
         return o, g
 
-    def step(self, obs):
-        actions = self.get_actions(obs['observation'], obs['achieved_goal'], obs['desired_goal'])
-        return actions, None, None, None
-
-
     def get_actions(self, o, ag, g, noise_eps=0., random_eps=0., use_target_net=False,
                     compute_Q=False):
         o, g = self._preprocess_og(o, ag, g)
@@ -157,30 +151,25 @@ class DDPG(object):
         else:
             return ret
 
-    def init_demo_buffer(self, demoDataFile, update_stats=True): #function that initializes the demo buffer
+    def initDemoBuffer(self, demoDataFile, update_stats=True): #function that initializes the demo buffer
 
         demoData = np.load(demoDataFile) #load the demonstration data from data file
         info_keys = [key.replace('info_', '') for key in self.input_dims.keys() if key.startswith('info_')]
-        info_values = [np.empty((self.T - 1, 1, self.input_dims['info_' + key]), np.float32) for key in info_keys]
-
-        demo_data_obs = demoData['obs']
-        demo_data_acs = demoData['acs']
-        demo_data_info = demoData['info']
+        info_values = [np.empty((self.T, 1, self.input_dims['info_' + key]), np.float32) for key in info_keys]
 
         for epsd in range(self.num_demo): # we initialize the whole demo buffer at the start of the training
             obs, acts, goals, achieved_goals = [], [] ,[] ,[]
             i = 0
-            for transition in range(self.T - 1):
-                obs.append([demo_data_obs[epsd][transition].get('observation')])
-                acts.append([demo_data_acs[epsd][transition]])
-                goals.append([demo_data_obs[epsd][transition].get('desired_goal')])
-                achieved_goals.append([demo_data_obs[epsd][transition].get('achieved_goal')])
+            for transition in range(self.T):
+                obs.append([demoData['obs'][epsd ][transition].get('observation')])
+                acts.append([demoData['acs'][epsd][transition]])
+                goals.append([demoData['obs'][epsd][transition].get('desired_goal')])
+                achieved_goals.append([demoData['obs'][epsd][transition].get('achieved_goal')])
                 for idx, key in enumerate(info_keys):
-                    info_values[idx][transition, i] = demo_data_info[epsd][transition][key]
+                    info_values[idx][transition, i] = demoData['info'][epsd][transition][key]
 
-
-            obs.append([demo_data_obs[epsd][self.T - 1].get('observation')])
-            achieved_goals.append([demo_data_obs[epsd][self.T - 1].get('achieved_goal')])
+            obs.append([demoData['obs'][epsd][self.T].get('observation')])
+            achieved_goals.append([demoData['obs'][epsd][self.T].get('achieved_goal')])
 
             episode = dict(o=obs,
                            u=acts,
@@ -190,9 +179,10 @@ class DDPG(object):
                 episode['info_{}'.format(key)] = value
 
             episode = convert_episode_to_batch_major(episode)
-            global DEMO_BUFFER
-            DEMO_BUFFER.store_episode(episode) # create the observation dict and append them into the demonstration buffer
-            logger.debug("Demo buffer size currently ", DEMO_BUFFER.get_current_size()) #print out the demonstration buffer size
+            global demoBuffer
+            demoBuffer.store_episode(episode) # create the observation dict and append them into the demonstration buffer
+
+            print("Demo buffer size currently ", demoBuffer.get_current_size()) #print out the demonstration buffer size
 
             if update_stats:
                 # add transitions to normalizer to normalize the demo data as well
@@ -201,7 +191,7 @@ class DDPG(object):
                 num_normalizing_transitions = transitions_in_episode_batch(episode)
                 transitions = self.sample_transitions(episode, num_normalizing_transitions)
 
-                o, g, ag = transitions['o'], transitions['g'], transitions['ag']
+                o, o_2, g, ag = transitions['o'], transitions['o_2'], transitions['g'], transitions['ag']
                 transitions['o'], transitions['g'] = self._preprocess_og(o, ag, g)
                 # No need to preprocess the o_2 and g_2 since this is only used for stats
 
@@ -212,8 +202,6 @@ class DDPG(object):
                 self.g_stats.recompute_stats()
             episode.clear()
 
-        logger.info("Demo buffer size: ", DEMO_BUFFER.get_current_size()) #print out the demonstration buffer size
-
     def store_episode(self, episode_batch, update_stats=True):
         """
         episode_batch: array of batch_size x (T or T+1) x dim_key
@@ -229,7 +217,7 @@ class DDPG(object):
             num_normalizing_transitions = transitions_in_episode_batch(episode_batch)
             transitions = self.sample_transitions(episode_batch, num_normalizing_transitions)
 
-            o, g, ag = transitions['o'], transitions['g'], transitions['ag']
+            o, o_2, g, ag = transitions['o'], transitions['o_2'], transitions['g'], transitions['ag']
             transitions['o'], transitions['g'] = self._preprocess_og(o, ag, g)
             # No need to preprocess the o_2 and g_2 since this is only used for stats
 
@@ -263,9 +251,9 @@ class DDPG(object):
     def sample_batch(self):
         if self.bc_loss: #use demonstration buffer to sample as well if bc_loss flag is set TRUE
             transitions = self.buffer.sample(self.batch_size - self.demo_batch_size)
-            global DEMO_BUFFER
-            transitions_demo = DEMO_BUFFER.sample(self.demo_batch_size) #sample from the demo buffer
-            for k, values in transitions_demo.items():
+            global demoBuffer
+            transitionsDemo = demoBuffer.sample(self.demo_batch_size) #sample from the demo buffer
+            for k, values in transitionsDemo.items():
                 rolloutV = transitions[k].tolist()
                 for v in values:
                     rolloutV.append(v.tolist())
@@ -314,7 +302,10 @@ class DDPG(object):
 
     def _create_network(self, reuse=False):
         logger.info("Creating a DDPG agent with action space %d x %s..." % (self.dimu, self.max_u))
-        self.sess = tf_util.get_session()
+
+        self.sess = tf.get_default_session()
+        if self.sess is None:
+            self.sess = tf.InteractiveSession()
 
         # running averages
         with tf.variable_scope('o_stats') as vs:
@@ -410,7 +401,7 @@ class DDPG(object):
         logs += [('stats_g/mean', np.mean(self.sess.run([self.g_stats.mean])))]
         logs += [('stats_g/std', np.mean(self.sess.run([self.g_stats.std])))]
 
-        if prefix != '' and not prefix.endswith('/'):
+        if prefix is not '' and not prefix.endswith('/'):
             return [(prefix + '/' + key, val) for key, val in logs]
         else:
             return logs
@@ -442,7 +433,3 @@ class DDPG(object):
         assert(len(vars) == len(state["tf"]))
         node = [tf.assign(var, val) for var, val in zip(vars, state["tf"])]
         self.sess.run(node)
-
-    def save(self, save_path):
-        tf_util.save_variables(save_path)
-

baselines/her/experiment/config.py

@@ -1,11 +1,10 @@
-import os
 import numpy as np
 import gym
 
 from baselines import logger
 from baselines.her.ddpg import DDPG
-from baselines.her.her_sampler import make_sample_her_transitions
-from baselines.bench.monitor import Monitor
+from baselines.her.her import make_sample_her_transitions
+
 
 DEFAULT_ENV_PARAMS = {
     'FetchReach-v1': {
@@ -73,32 +72,16 @@ def cached_make_env(make_env):
 def prepare_params(kwargs):
     # DDPG params
     ddpg_params = dict()
+
     env_name = kwargs['env_name']
 
-    def make_env(subrank=None):
-        env = gym.make(env_name)
-        if subrank is not None and logger.get_dir() is not None:
-            try:
-                from mpi4py import MPI
-                mpi_rank = MPI.COMM_WORLD.Get_rank()
-            except ImportError:
-                MPI = None
-                mpi_rank = 0
-                logger.warn('Running with a single MPI process. This should work, but the results may differ from the ones publshed in Plappert et al.')
-
-            max_episode_steps = env._max_episode_steps
-            env =  Monitor(env,
-                           os.path.join(logger.get_dir(), str(mpi_rank) + '.' + str(subrank)),
-                           allow_early_resets=True)
-            # hack to re-expose _max_episode_steps (ideally should replace reliance on it downstream)
-            env = gym.wrappers.TimeLimit(env, max_episode_steps=max_episode_steps)
-        return env
-
+    def make_env():
+        return gym.make(env_name)
     kwargs['make_env'] = make_env
     tmp_env = cached_make_env(kwargs['make_env'])
     assert hasattr(tmp_env, '_max_episode_steps')
     kwargs['T'] = tmp_env._max_episode_steps
-
+    tmp_env.reset()
     kwargs['max_u'] = np.array(kwargs['max_u']) if isinstance(kwargs['max_u'], list) else kwargs['max_u']
     kwargs['gamma'] = 1. - 1. / kwargs['T']
     if 'lr' in kwargs:

baselines/her/experiment/data_generation/fetch_data_generation.py

@@ -1,5 +1,18 @@
 import gym
+import time
+import random
 import numpy as np
+import rospy
+import roslaunch
+
+from random import randint
+from std_srvs.srv import Empty
+from sensor_msgs.msg import JointState
+from geometry_msgs.msg import PoseStamped
+from geometry_msgs.msg import Pose
+from std_msgs.msg import Float64
+from controller_manager_msgs.srv import SwitchController
+from gym.utils import seeding
 
 
 """Data generation for the case of a single block pick and place in Fetch Env"""
@@ -9,7 +22,7 @@ observations = []
 infos = []
 
 def main():
-    env = gym.make('FetchPickAndPlace-v1')
+    env = gym.make('FetchPickAndPlace-v0')
     numItr = 100
     initStateSpace = "random"
     env.reset()
@@ -18,19 +31,21 @@ def main():
         obs = env.reset()
         print("ITERATION NUMBER ", len(actions))
         goToGoal(env, obs)
-
+        
 
     fileName = "data_fetch"
     fileName += "_" + initStateSpace
     fileName += "_" + str(numItr)
     fileName += ".npz"
-
+    
     np.savez_compressed(fileName, acs=actions, obs=observations, info=infos) # save the file
 
 def goToGoal(env, lastObs):
 
     goal = lastObs['desired_goal']
     objectPos = lastObs['observation'][3:6]
+    gripperPos = lastObs['observation'][:3]
+    gripperState = lastObs['observation'][9:11]
     object_rel_pos = lastObs['observation'][6:9]
     episodeAcs = []
     episodeObs = []
@@ -38,7 +53,7 @@ def goToGoal(env, lastObs):
 
     object_oriented_goal = object_rel_pos.copy()
     object_oriented_goal[2] += 0.03 # first make the gripper go slightly above the object
-
+    
     timeStep = 0 #count the total number of timesteps
     episodeObs.append(lastObs)
 
@@ -61,6 +76,8 @@ def goToGoal(env, lastObs):
         episodeObs.append(obsDataNew)
 
         objectPos = obsDataNew['observation'][3:6]
+        gripperPos = obsDataNew['observation'][:3]
+        gripperState = obsDataNew['observation'][9:11]
         object_rel_pos = obsDataNew['observation'][6:9]
 
     while np.linalg.norm(object_rel_pos) >= 0.005 and timeStep <= env._max_episode_steps :
@@ -79,6 +96,8 @@ def goToGoal(env, lastObs):
         episodeObs.append(obsDataNew)
 
         objectPos = obsDataNew['observation'][3:6]
+        gripperPos = obsDataNew['observation'][:3]
+        gripperState = obsDataNew['observation'][9:11]
         object_rel_pos = obsDataNew['observation'][6:9]
 
 
@@ -98,6 +117,8 @@ def goToGoal(env, lastObs):
         episodeObs.append(obsDataNew)
 
         objectPos = obsDataNew['observation'][3:6]
+        gripperPos = obsDataNew['observation'][:3]
+        gripperState = obsDataNew['observation'][9:11]
         object_rel_pos = obsDataNew['observation'][6:9]
 
     while True: #limit the number of timesteps in the episode to a fixed duration
@@ -113,6 +134,8 @@ def goToGoal(env, lastObs):
         episodeObs.append(obsDataNew)
 
         objectPos = obsDataNew['observation'][3:6]
+        gripperPos = obsDataNew['observation'][:3]
+        gripperState = obsDataNew['observation'][9:11]
         object_rel_pos = obsDataNew['observation'][6:9]
 
         if timeStep >= env._max_episode_steps: break

baselines/her/experiment/play.py

@@ -1,4 +1,3 @@
-# DEPRECATED, use --play flag to baselines.run instead
 import click
 import numpy as np
 import pickle

baselines/her/experiment/plot.py

@@ -1,5 +1,3 @@
-# DEPRECATED, use baselines.common.plot_util instead
-
 import os
 import matplotlib.pyplot as plt
 import numpy as np

baselines/her/experiment/train.py

@@ -0,0 +1,194 @@
+import os
+import sys
+
+import click
+import numpy as np
+import json
+from mpi4py import MPI
+
+from baselines import logger
+from baselines.common import set_global_seeds
+from baselines.common.mpi_moments import mpi_moments
+import baselines.her.experiment.config as config
+from baselines.her.rollout import RolloutWorker
+from baselines.her.util import mpi_fork
+
+from subprocess import CalledProcessError
+
+
+def mpi_average(value):
+    if value == []:
+        value = [0.]
+    if not isinstance(value, list):
+        value = [value]
+    return mpi_moments(np.array(value))[0]
+
+
+def train(policy, rollout_worker, evaluator,
+          n_epochs, n_test_rollouts, n_cycles, n_batches, policy_save_interval,
+          save_policies, demo_file, **kwargs):
+    rank = MPI.COMM_WORLD.Get_rank()
+
+    latest_policy_path = os.path.join(logger.get_dir(), 'policy_latest.pkl')
+    best_policy_path = os.path.join(logger.get_dir(), 'policy_best.pkl')
+    periodic_policy_path = os.path.join(logger.get_dir(), 'policy_{}.pkl')
+
+    logger.info("Training...")
+    best_success_rate = -1
+
+    if policy.bc_loss == 1: policy.initDemoBuffer(demo_file) #initialize demo buffer if training with demonstrations
+    for epoch in range(n_epochs):
+        # train
+        rollout_worker.clear_history()
+        for _ in range(n_cycles):
+            episode = rollout_worker.generate_rollouts()
+            policy.store_episode(episode)
+            for _ in range(n_batches):
+                policy.train()
+            policy.update_target_net()
+
+        # test
+        evaluator.clear_history()
+        for _ in range(n_test_rollouts):
+            evaluator.generate_rollouts()
+
+        # record logs
+        logger.record_tabular('epoch', epoch)
+        for key, val in evaluator.logs('test'):
+            logger.record_tabular(key, mpi_average(val))
+        for key, val in rollout_worker.logs('train'):
+            logger.record_tabular(key, mpi_average(val))
+        for key, val in policy.logs():
+            logger.record_tabular(key, mpi_average(val))
+
+        if rank == 0:
+            logger.dump_tabular()
+
+        # save the policy if it's better than the previous ones
+        success_rate = mpi_average(evaluator.current_success_rate())
+        if rank == 0 and success_rate >= best_success_rate and save_policies:
+            best_success_rate = success_rate
+            logger.info('New best success rate: {}. Saving policy to {} ...'.format(best_success_rate, best_policy_path))
+            evaluator.save_policy(best_policy_path)
+            evaluator.save_policy(latest_policy_path)
+        if rank == 0 and policy_save_interval > 0 and epoch % policy_save_interval == 0 and save_policies:
+            policy_path = periodic_policy_path.format(epoch)
+            logger.info('Saving periodic policy to {} ...'.format(policy_path))
+            evaluator.save_policy(policy_path)
+
+        # make sure that different threads have different seeds
+        local_uniform = np.random.uniform(size=(1,))
+        root_uniform = local_uniform.copy()
+        MPI.COMM_WORLD.Bcast(root_uniform, root=0)
+        if rank != 0:
+            assert local_uniform[0] != root_uniform[0]
+
+
+def launch(
+    env, logdir, n_epochs, num_cpu, seed, replay_strategy, policy_save_interval, clip_return,
+    demo_file, override_params={}, save_policies=True
+):
+    # Fork for multi-CPU MPI implementation.
+    if num_cpu > 1:
+        try:
+            whoami = mpi_fork(num_cpu, ['--bind-to', 'core'])
+        except CalledProcessError:
+            # fancy version of mpi call failed, try simple version
+            whoami = mpi_fork(num_cpu)
+
+        if whoami == 'parent':
+            sys.exit(0)
+        import baselines.common.tf_util as U
+        U.single_threaded_session().__enter__()
+    rank = MPI.COMM_WORLD.Get_rank()
+
+    # Configure logging
+    if rank == 0:
+        if logdir or logger.get_dir() is None:
+            logger.configure(dir=logdir)
+    else:
+        logger.configure()
+    logdir = logger.get_dir()
+    assert logdir is not None
+    os.makedirs(logdir, exist_ok=True)
+
+    # Seed everything.
+    rank_seed = seed + 1000000 * rank
+    set_global_seeds(rank_seed)
+
+    # Prepare params.
+    params = config.DEFAULT_PARAMS
+    params['env_name'] = env
+    params['replay_strategy'] = replay_strategy
+    if env in config.DEFAULT_ENV_PARAMS:
+        params.update(config.DEFAULT_ENV_PARAMS[env])  # merge env-specific parameters in
+    params.update(**override_params)  # makes it possible to override any parameter
+    with open(os.path.join(logger.get_dir(), 'params.json'), 'w') as f:
+        json.dump(params, f)
+    params = config.prepare_params(params)
+    config.log_params(params, logger=logger)
+
+    if num_cpu == 1:
+        logger.warn()
+        logger.warn('*** Warning ***')
+        logger.warn(
+            'You are running HER with just a single MPI worker. This will work, but the ' +
+            'experiments that we report in Plappert et al. (2018, https://arxiv.org/abs/1802.09464) ' +
+            'were obtained with --num_cpu 19. This makes a significant difference and if you ' +
+            'are looking to reproduce those results, be aware of this. Please also refer to ' +
+            'https://github.com/openai/baselines/issues/314 for further details.')
+        logger.warn('****************')
+        logger.warn()
+
+    dims = config.configure_dims(params)
+    policy = config.configure_ddpg(dims=dims, params=params, clip_return=clip_return)
+
+    rollout_params = {
+        'exploit': False,
+        'use_target_net': False,
+        'use_demo_states': True,
+        'compute_Q': False,
+        'T': params['T'],
+    }
+
+    eval_params = {
+        'exploit': True,
+        'use_target_net': params['test_with_polyak'],
+        'use_demo_states': False,
+        'compute_Q': True,
+        'T': params['T'],
+    }
+
+    for name in ['T', 'rollout_batch_size', 'gamma', 'noise_eps', 'random_eps']:
+        rollout_params[name] = params[name]
+        eval_params[name] = params[name]
+
+    rollout_worker = RolloutWorker(params['make_env'], policy, dims, logger, **rollout_params)
+    rollout_worker.seed(rank_seed)
+
+    evaluator = RolloutWorker(params['make_env'], policy, dims, logger, **eval_params)
+    evaluator.seed(rank_seed)
+
+    train(
+        logdir=logdir, policy=policy, rollout_worker=rollout_worker,
+        evaluator=evaluator, n_epochs=n_epochs, n_test_rollouts=params['n_test_rollouts'],
+        n_cycles=params['n_cycles'], n_batches=params['n_batches'],
+        policy_save_interval=policy_save_interval, save_policies=save_policies, demo_file=demo_file)
+
+
+@click.command()
+@click.option('--env', type=str, default='FetchReach-v1', help='the name of the OpenAI Gym environment that you want to train on')
+@click.option('--logdir', type=str, default=None, help='the path to where logs and policy pickles should go. If not specified, creates a folder in /tmp/')
+@click.option('--n_epochs', type=int, default=50, help='the number of training epochs to run')
+@click.option('--num_cpu', type=int, default=1, help='the number of CPU cores to use (using MPI)')
+@click.option('--seed', type=int, default=0, help='the random seed used to seed both the environment and the training code')
+@click.option('--policy_save_interval', type=int, default=5, help='the interval with which policy pickles are saved. If set to 0, only the best and latest policy will be pickled.')
+@click.option('--replay_strategy', type=click.Choice(['future', 'none']), default='future', help='the HER replay strategy to be used. "future" uses HER, "none" disables HER.')
+@click.option('--clip_return', type=int, default=1, help='whether or not returns should be clipped')
+@click.option('--demo_file', type=str, default = 'PATH/TO/DEMO/DATA/FILE.npz', help='demo data file path')
+def main(**kwargs):
+    launch(**kwargs)
+
+
+if __name__ == '__main__':
+    main()

baselines/her/her.py

@@ -1,193 +1,63 @@
-import os
-
-import click
 import numpy as np
-import json
-from mpi4py import MPI
-
-from baselines import logger
-from baselines.common import set_global_seeds, tf_util
-from baselines.common.mpi_moments import mpi_moments
-import baselines.her.experiment.config as config
-from baselines.her.rollout import RolloutWorker
-
-def mpi_average(value):
-    if not isinstance(value, list):
-        value = [value]
-    if not any(value):
-        value = [0.]
-    return mpi_moments(np.array(value))[0]
 
 
-def train(*, policy, rollout_worker, evaluator,
-          n_epochs, n_test_rollouts, n_cycles, n_batches, policy_save_interval,
-          save_path, demo_file, **kwargs):
-    rank = MPI.COMM_WORLD.Get_rank()
+def make_sample_her_transitions(replay_strategy, replay_k, reward_fun):
+    """Creates a sample function that can be used for HER experience replay.
 
-    if save_path:
-        latest_policy_path = os.path.join(save_path, 'policy_latest.pkl')
-        best_policy_path = os.path.join(save_path, 'policy_best.pkl')
-        periodic_policy_path = os.path.join(save_path, 'policy_{}.pkl')
+    Args:
+        replay_strategy (in ['future', 'none']): the HER replay strategy; if set to 'none',
+            regular DDPG experience replay is used
+        replay_k (int): the ratio between HER replays and regular replays (e.g. k = 4 -> 4 times
+            as many HER replays as regular replays are used)
+        reward_fun (function): function to re-compute the reward with substituted goals
+    """
+    if replay_strategy == 'future':
+        future_p = 1 - (1. / (1 + replay_k))
+    else:  # 'replay_strategy' == 'none'
+        future_p = 0
 
-    logger.info("Training...")
-    best_success_rate = -1
+    def _sample_her_transitions(episode_batch, batch_size_in_transitions):
+        """episode_batch is {key: array(buffer_size x T x dim_key)}
+        """
+        T = episode_batch['u'].shape[1]
+        rollout_batch_size = episode_batch['u'].shape[0]
+        batch_size = batch_size_in_transitions
 
-    if policy.bc_loss == 1: policy.init_demo_buffer(demo_file) #initialize demo buffer if training with demonstrations
+        # Select which episodes and time steps to use.
+        episode_idxs = np.random.randint(0, rollout_batch_size, batch_size)
+        t_samples = np.random.randint(T, size=batch_size)
+        transitions = {key: episode_batch[key][episode_idxs, t_samples].copy()
+                       for key in episode_batch.keys()}
 
-    # num_timesteps = n_epochs * n_cycles * rollout_length * number of rollout workers
-    for epoch in range(n_epochs):
-        # train
-        rollout_worker.clear_history()
-        for _ in range(n_cycles):
-            episode = rollout_worker.generate_rollouts()
-            policy.store_episode(episode)
-            for _ in range(n_batches):
-                policy.train()
-            policy.update_target_net()
+        # Select future time indexes proportional with probability future_p. These
+        # will be used for HER replay by substituting in future goals.
+        her_indexes = np.where(np.random.uniform(size=batch_size) < future_p)
+        future_offset = np.random.uniform(size=batch_size) * (T - t_samples)
+        future_offset = future_offset.astype(int)
+        future_t = (t_samples + 1 + future_offset)[her_indexes]
 
-        # test
-        evaluator.clear_history()
-        for _ in range(n_test_rollouts):
-            evaluator.generate_rollouts()
+        # Replace goal with achieved goal but only for the previously-selected
+        # HER transitions (as defined by her_indexes). For the other transitions,
+        # keep the original goal.
+        future_ag = episode_batch['ag'][episode_idxs[her_indexes], future_t]
+        transitions['g'][her_indexes] = future_ag
 
-        # record logs
-        logger.record_tabular('epoch', epoch)
-        for key, val in evaluator.logs('test'):
-            logger.record_tabular(key, mpi_average(val))
-        for key, val in rollout_worker.logs('train'):
-            logger.record_tabular(key, mpi_average(val))
-        for key, val in policy.logs():
-            logger.record_tabular(key, mpi_average(val))
+        # Reconstruct info dictionary for reward  computation.
+        info = {}
+        for key, value in transitions.items():
+            if key.startswith('info_'):
+                info[key.replace('info_', '')] = value
 
-        if rank == 0:
-            logger.dump_tabular()
+        # Re-compute reward since we may have substituted the goal.
+        reward_params = {k: transitions[k] for k in ['ag_2', 'g']}
+        reward_params['info'] = info
+        transitions['r'] = reward_fun(**reward_params)
 
-        # save the policy if it's better than the previous ones
-        success_rate = mpi_average(evaluator.current_success_rate())
-        if rank == 0 and success_rate >= best_success_rate and save_path:
-            best_success_rate = success_rate
-            logger.info('New best success rate: {}. Saving policy to {} ...'.format(best_success_rate, best_policy_path))
-            evaluator.save_policy(best_policy_path)
-            evaluator.save_policy(latest_policy_path)
-        if rank == 0 and policy_save_interval > 0 and epoch % policy_save_interval == 0 and save_path:
-            policy_path = periodic_policy_path.format(epoch)
-            logger.info('Saving periodic policy to {} ...'.format(policy_path))
-            evaluator.save_policy(policy_path)
+        transitions = {k: transitions[k].reshape(batch_size, *transitions[k].shape[1:])
+                       for k in transitions.keys()}
 
-        # make sure that different threads have different seeds
-        local_uniform = np.random.uniform(size=(1,))
-        root_uniform = local_uniform.copy()
-        MPI.COMM_WORLD.Bcast(root_uniform, root=0)
-        if rank != 0:
-            assert local_uniform[0] != root_uniform[0]
+        assert(transitions['u'].shape[0] == batch_size_in_transitions)
 
-    return policy
+        return transitions
 
-
-def learn(*, network, env, total_timesteps,
-    seed=None,
-    eval_env=None,
-    replay_strategy='future',
-    policy_save_interval=5,
-    clip_return=True,
-    demo_file=None,
-    override_params=None,
-    load_path=None,
-    save_path=None,
-    **kwargs
-):
-
-    override_params = override_params or {}
-    if MPI is not None:
-        rank = MPI.COMM_WORLD.Get_rank()
-        num_cpu = MPI.COMM_WORLD.Get_size()
-
-    # Seed everything.
-    rank_seed = seed + 1000000 * rank if seed is not None else None
-    set_global_seeds(rank_seed)
-
-    # Prepare params.
-    params = config.DEFAULT_PARAMS
-    env_name = env.spec.id
-    params['env_name'] = env_name
-    params['replay_strategy'] = replay_strategy
-    if env_name in config.DEFAULT_ENV_PARAMS:
-        params.update(config.DEFAULT_ENV_PARAMS[env_name])  # merge env-specific parameters in
-    params.update(**override_params)  # makes it possible to override any parameter
-    with open(os.path.join(logger.get_dir(), 'params.json'), 'w') as f:
-         json.dump(params, f)
-    params = config.prepare_params(params)
-    params['rollout_batch_size'] = env.num_envs
-
-    if demo_file is not None:
-        params['bc_loss'] = 1
-    params.update(kwargs)
-
-    config.log_params(params, logger=logger)
-
-    if num_cpu == 1:
-        logger.warn()
-        logger.warn('*** Warning ***')
-        logger.warn(
-            'You are running HER with just a single MPI worker. This will work, but the ' +
-            'experiments that we report in Plappert et al. (2018, https://arxiv.org/abs/1802.09464) ' +
-            'were obtained with --num_cpu 19. This makes a significant difference and if you ' +
-            'are looking to reproduce those results, be aware of this. Please also refer to ' +
-            'https://github.com/openai/baselines/issues/314 for further details.')
-        logger.warn('****************')
-        logger.warn()
-
-    dims = config.configure_dims(params)
-    policy = config.configure_ddpg(dims=dims, params=params, clip_return=clip_return)
-    if load_path is not None:
-        tf_util.load_variables(load_path)
-
-    rollout_params = {
-        'exploit': False,
-        'use_target_net': False,
-        'use_demo_states': True,
-        'compute_Q': False,
-        'T': params['T'],
-    }
-
-    eval_params = {
-        'exploit': True,
-        'use_target_net': params['test_with_polyak'],
-        'use_demo_states': False,
-        'compute_Q': True,
-        'T': params['T'],
-    }
-
-    for name in ['T', 'rollout_batch_size', 'gamma', 'noise_eps', 'random_eps']:
-        rollout_params[name] = params[name]
-        eval_params[name] = params[name]
-
-    eval_env = eval_env or env
-
-    rollout_worker = RolloutWorker(env, policy, dims, logger, monitor=True, **rollout_params)
-    evaluator = RolloutWorker(eval_env, policy, dims, logger, **eval_params)
-
-    n_cycles = params['n_cycles']
-    n_epochs = total_timesteps // n_cycles // rollout_worker.T // rollout_worker.rollout_batch_size
-
-    return train(
-        save_path=save_path, policy=policy, rollout_worker=rollout_worker,
-        evaluator=evaluator, n_epochs=n_epochs, n_test_rollouts=params['n_test_rollouts'],
-        n_cycles=params['n_cycles'], n_batches=params['n_batches'],
-        policy_save_interval=policy_save_interval, demo_file=demo_file)
-
-
-@click.command()
-@click.option('--env', type=str, default='FetchReach-v1', help='the name of the OpenAI Gym environment that you want to train on')
-@click.option('--total_timesteps', type=int, default=int(5e5), help='the number of timesteps to run')
-@click.option('--seed', type=int, default=0, help='the random seed used to seed both the environment and the training code')
-@click.option('--policy_save_interval', type=int, default=5, help='the interval with which policy pickles are saved. If set to 0, only the best and latest policy will be pickled.')
-@click.option('--replay_strategy', type=click.Choice(['future', 'none']), default='future', help='the HER replay strategy to be used. "future" uses HER, "none" disables HER.')
-@click.option('--clip_return', type=int, default=1, help='whether or not returns should be clipped')
-@click.option('--demo_file', type=str, default = 'PATH/TO/DEMO/DATA/FILE.npz', help='demo data file path')
-def main(**kwargs):
-    learn(**kwargs)
-
-
-if __name__ == '__main__':
-    main()
+    return _sample_her_transitions

baselines/her/her_sampler.py

@@ -1,63 +0,0 @@
-import numpy as np
-
-
-def make_sample_her_transitions(replay_strategy, replay_k, reward_fun):
-    """Creates a sample function that can be used for HER experience replay.
-
-    Args:
-        replay_strategy (in ['future', 'none']): the HER replay strategy; if set to 'none',
-            regular DDPG experience replay is used
-        replay_k (int): the ratio between HER replays and regular replays (e.g. k = 4 -> 4 times
-            as many HER replays as regular replays are used)
-        reward_fun (function): function to re-compute the reward with substituted goals
-    """
-    if replay_strategy == 'future':
-        future_p = 1 - (1. / (1 + replay_k))
-    else:  # 'replay_strategy' == 'none'
-        future_p = 0
-
-    def _sample_her_transitions(episode_batch, batch_size_in_transitions):
-        """episode_batch is {key: array(buffer_size x T x dim_key)}
-        """
-        T = episode_batch['u'].shape[1]
-        rollout_batch_size = episode_batch['u'].shape[0]
-        batch_size = batch_size_in_transitions
-
-        # Select which episodes and time steps to use.
-        episode_idxs = np.random.randint(0, rollout_batch_size, batch_size)
-        t_samples = np.random.randint(T, size=batch_size)
-        transitions = {key: episode_batch[key][episode_idxs, t_samples].copy()
-                       for key in episode_batch.keys()}
-
-        # Select future time indexes proportional with probability future_p. These
-        # will be used for HER replay by substituting in future goals.
-        her_indexes = np.where(np.random.uniform(size=batch_size) < future_p)
-        future_offset = np.random.uniform(size=batch_size) * (T - t_samples)
-        future_offset = future_offset.astype(int)
-        future_t = (t_samples + 1 + future_offset)[her_indexes]
-
-        # Replace goal with achieved goal but only for the previously-selected
-        # HER transitions (as defined by her_indexes). For the other transitions,
-        # keep the original goal.
-        future_ag = episode_batch['ag'][episode_idxs[her_indexes], future_t]
-        transitions['g'][her_indexes] = future_ag
-
-        # Reconstruct info dictionary for reward  computation.
-        info = {}
-        for key, value in transitions.items():
-            if key.startswith('info_'):
-                info[key.replace('info_', '')] = value
-
-        # Re-compute reward since we may have substituted the goal.
-        reward_params = {k: transitions[k] for k in ['ag_2', 'g']}
-        reward_params['info'] = info
-        transitions['r'] = reward_fun(**reward_params)
-
-        transitions = {k: transitions[k].reshape(batch_size, *transitions[k].shape[1:])
-                       for k in transitions.keys()}
-
-        assert(transitions['u'].shape[0] == batch_size_in_transitions)
-
-        return transitions
-
-    return _sample_her_transitions

baselines/her/rollout.py

@@ -2,6 +2,7 @@ from collections import deque
 
 import numpy as np
 import pickle
+from mujoco_py import MujocoException
 
 from baselines.her.util import convert_episode_to_batch_major, store_args
 
@@ -9,9 +10,9 @@ from baselines.her.util import convert_episode_to_batch_major, store_args
 class RolloutWorker:
 
     @store_args
-    def __init__(self, venv, policy, dims, logger, T, rollout_batch_size=1,
+    def __init__(self, make_env, policy, dims, logger, T, rollout_batch_size=1,
                  exploit=False, use_target_net=False, compute_Q=False, noise_eps=0,
-                 random_eps=0, history_len=100, render=False, monitor=False, **kwargs):
+                 random_eps=0, history_len=100, render=False, **kwargs):
         """Rollout worker generates experience by interacting with one or many environments.
 
         Args:
@@ -30,7 +31,7 @@ class RolloutWorker:
             history_len (int): length of history for statistics smoothing
             render (boolean): whether or not to render the rollouts
         """
-
+        self.envs = [make_env() for _ in range(rollout_batch_size)]
         assert self.T > 0
 
         self.info_keys = [key.replace('info_', '') for key in dims.keys() if key.startswith('info_')]
@@ -39,14 +40,26 @@ class RolloutWorker:
         self.Q_history = deque(maxlen=history_len)
 
         self.n_episodes = 0
+        self.g = np.empty((self.rollout_batch_size, self.dims['g']), np.float32)  # goals
+        self.initial_o = np.empty((self.rollout_batch_size, self.dims['o']), np.float32)  # observations
+        self.initial_ag = np.empty((self.rollout_batch_size, self.dims['g']), np.float32)  # achieved goals
         self.reset_all_rollouts()
         self.clear_history()
 
+    def reset_rollout(self, i):
+        """Resets the `i`-th rollout environment, re-samples a new goal, and updates the `initial_o`
+        and `g` arrays accordingly.
+        """
+        obs = self.envs[i].reset()
+        self.initial_o[i] = obs['observation']
+        self.initial_ag[i] = obs['achieved_goal']
+        self.g[i] = obs['desired_goal']
+
     def reset_all_rollouts(self):
-        self.obs_dict = self.venv.reset()
-        self.initial_o = self.obs_dict['observation']
-        self.initial_ag = self.obs_dict['achieved_goal']
-        self.g = self.obs_dict['desired_goal']
+        """Resets all `rollout_batch_size` rollout workers.
+        """
+        for i in range(self.rollout_batch_size):
+            self.reset_rollout(i)
 
     def generate_rollouts(self):
         """Performs `rollout_batch_size` rollouts in parallel for time horizon `T` with the current
@@ -62,8 +75,7 @@ class RolloutWorker:
 
         # generate episodes
         obs, achieved_goals, acts, goals, successes = [], [], [], [], []
-        dones = []
-        info_values = [np.empty((self.T - 1, self.rollout_batch_size, self.dims['info_' + key]), np.float32) for key in self.info_keys]
+        info_values = [np.empty((self.T, self.rollout_batch_size, self.dims['info_' + key]), np.float32) for key in self.info_keys]
         Qs = []
         for t in range(self.T):
             policy_output = self.policy.get_actions(
@@ -87,27 +99,27 @@ class RolloutWorker:
             ag_new = np.empty((self.rollout_batch_size, self.dims['g']))
             success = np.zeros(self.rollout_batch_size)
             # compute new states and observations
-            obs_dict_new, _, done, info = self.venv.step(u)
-            o_new = obs_dict_new['observation']
-            ag_new = obs_dict_new['achieved_goal']
-            success = np.array([i.get('is_success', 0.0) for i in info])
-
-            if any(done):
-                # here we assume all environments are done is ~same number of steps, so we terminate rollouts whenever any of the envs returns done
-                # trick with using vecenvs is not to add the obs from the environments that are "done", because those are already observations
-                # after a reset
-                break
-
-            for i, info_dict in enumerate(info):
-                for idx, key in enumerate(self.info_keys):
-                    info_values[idx][t, i] = info[i][key]
+            for i in range(self.rollout_batch_size):
+                try:
+                    # We fully ignore the reward here because it will have to be re-computed
+                    # for HER.
+                    curr_o_new, _, _, info = self.envs[i].step(u[i])
+                    if 'is_success' in info:
+                        success[i] = info['is_success']
+                    o_new[i] = curr_o_new['observation']
+                    ag_new[i] = curr_o_new['achieved_goal']
+                    for idx, key in enumerate(self.info_keys):
+                        info_values[idx][t, i] = info[key]
+                    if self.render:
+                        self.envs[i].render()
+                except MujocoException as e:
+                    return self.generate_rollouts()
 
             if np.isnan(o_new).any():
                 self.logger.warn('NaN caught during rollout generation. Trying again...')
                 self.reset_all_rollouts()
                 return self.generate_rollouts()
 
-            dones.append(done)
             obs.append(o.copy())
             achieved_goals.append(ag.copy())
             successes.append(success.copy())
@@ -117,6 +129,7 @@ class RolloutWorker:
             ag[...] = ag_new
         obs.append(o.copy())
         achieved_goals.append(ag.copy())
+        self.initial_o[:] = o
 
         episode = dict(o=obs,
                        u=acts,
@@ -163,8 +176,13 @@ class RolloutWorker:
             logs += [('mean_Q', np.mean(self.Q_history))]
         logs += [('episode', self.n_episodes)]
 
-        if prefix != '' and not prefix.endswith('/'):
+        if prefix is not '' and not prefix.endswith('/'):
             return [(prefix + '/' + key, val) for key, val in logs]
         else:
             return logs
 
+    def seed(self, seed):
+        """Seeds each environment with a distinct seed derived from the passed in global seed.
+        """
+        for idx, env in enumerate(self.envs):
+            env.seed(seed + 1000 * idx)

baselines/logger.py

@@ -7,7 +7,6 @@ import time
 import datetime
 import tempfile
 from collections import defaultdict
-from contextlib import contextmanager
 
 DEBUG = 10
 INFO = 20
@@ -69,8 +68,7 @@ class HumanOutputFormat(KVWriter, SeqWriter):
         self.file.flush()
 
     def _truncate(self, s):
-        maxlen = 30
-        return s[:maxlen-3] + '...' if len(s) > maxlen else s
+        return s[:20] + '...' if len(s) > 23 else s
 
     def writeseq(self, seq):
         seq = list(seq)
@@ -197,13 +195,13 @@ def logkv(key, val):
     Call this once for each diagnostic quantity, each iteration
     If called many times, last value will be used.
     """
-    get_current().logkv(key, val)
+    Logger.CURRENT.logkv(key, val)
 
 def logkv_mean(key, val):
     """
     The same as logkv(), but if called many times, values averaged.
     """
-    get_current().logkv_mean(key, val)
+    Logger.CURRENT.logkv_mean(key, val)
 
 def logkvs(d):
     """
@@ -215,18 +213,21 @@ def logkvs(d):
 def dumpkvs():
     """
     Write all of the diagnostics from the current iteration
+
+    level: int. (see logger.py docs) If the global logger level is higher than
+                the level argument here, don't print to stdout.
     """
-    return get_current().dumpkvs()
+    Logger.CURRENT.dumpkvs()
 
 def getkvs():
-    return get_current().name2val
+    return Logger.CURRENT.name2val
 
 
 def log(*args, level=INFO):
     """
     Write the sequence of args, with no separators, to the console and output files (if you've configured an output file).
     """
-    get_current().log(*args, level=level)
+    Logger.CURRENT.log(*args, level=level)
 
 def debug(*args):
     log(*args, level=DEBUG)
@@ -245,29 +246,30 @@ def set_level(level):
     """
     Set logging threshold on current logger.
     """
-    get_current().set_level(level)
-
-def set_comm(comm):
-    get_current().set_comm(comm)
+    Logger.CURRENT.set_level(level)
 
 def get_dir():
     """
     Get directory that log files are being written to.
     will be None if there is no output directory (i.e., if you didn't call start)
     """
-    return get_current().get_dir()
+    return Logger.CURRENT.get_dir()
 
 record_tabular = logkv
 dump_tabular = dumpkvs
 
-@contextmanager
-def profile_kv(scopename):
-    logkey = 'wait_' + scopename
-    tstart = time.time()
-    try:
-        yield
-    finally:
-        get_current().name2val[logkey] += time.time() - tstart
+class ProfileKV:
+    """
+    Usage:
+    with logger.ProfileKV("interesting_scope"):
+        code
+    """
+    def __init__(self, n):
+        self.n = "wait_" + n
+    def __enter__(self):
+        self.t1 = time.time()
+    def __exit__(self ,type, value, traceback):
+        Logger.CURRENT.name2val[self.n] += time.time() - self.t1
 
 def profile(n):
     """
@@ -277,7 +279,7 @@ def profile(n):
     """
     def decorator_with_name(func):
         def func_wrapper(*args, **kwargs):
-            with profile_kv(n):
+            with ProfileKV(n):
                 return func(*args, **kwargs)
         return func_wrapper
     return decorator_with_name
@@ -287,25 +289,17 @@ def profile(n):
 # Backend
 # ================================================================
 
-def get_current():
-    if Logger.CURRENT is None:
-        _configure_default_logger()
-
-    return Logger.CURRENT
-
-
 class Logger(object):
     DEFAULT = None  # A logger with no output files. (See right below class definition)
                     # So that you can still log to the terminal without setting up any output files
     CURRENT = None  # Current logger being used by the free functions above
 
-    def __init__(self, dir, output_formats, comm=None):
+    def __init__(self, dir, output_formats):
         self.name2val = defaultdict(float)  # values this iteration
         self.name2cnt = defaultdict(int)
         self.level = INFO
         self.dir = dir
         self.output_formats = output_formats
-        self.comm = comm
 
     # Logging API, forwarded
     # ----------------------------------------
@@ -313,27 +307,20 @@ class Logger(object):
         self.name2val[key] = val
 
     def logkv_mean(self, key, val):
+        if val is None:
+            self.name2val[key] = None
+            return
         oldval, cnt = self.name2val[key], self.name2cnt[key]
         self.name2val[key] = oldval*cnt/(cnt+1) + val/(cnt+1)
         self.name2cnt[key] = cnt + 1
 
     def dumpkvs(self):
-        if self.comm is None:
-            d = self.name2val
-        else:
-            from baselines.common import mpi_util
-            d = mpi_util.mpi_weighted_mean(self.comm,
-                {name : (val, self.name2cnt.get(name, 1))
-                    for (name, val) in self.name2val.items()})
-            if self.comm.rank != 0:
-                d['dummy'] = 1 # so we don't get a warning about empty dict
-        out = d.copy() # Return the dict for unit testing purposes
+        if self.level == DISABLED: return
         for fmt in self.output_formats:
             if isinstance(fmt, KVWriter):
-                fmt.writekvs(d)
+                fmt.writekvs(self.name2val)
         self.name2val.clear()
         self.name2cnt.clear()
-        return out
 
     def log(self, *args, level=INFO):
         if self.level <= level:
@@ -344,9 +331,6 @@ class Logger(object):
     def set_level(self, level):
         self.level = level
 
-    def set_comm(self, comm):
-        self.comm = comm
-
     def get_dir(self):
         return self.dir
 
@@ -361,10 +345,7 @@ class Logger(object):
             if isinstance(fmt, SeqWriter):
                 fmt.writeseq(map(str, args))
 
-def configure(dir=None, format_strs=None, comm=None):
-    """
-    If comm is provided, average all numerical stats across that comm
-    """
+def configure(dir=None, format_strs=None):
     if dir is None:
         dir = os.getenv('OPENAI_LOGDIR')
     if dir is None:
@@ -391,11 +372,15 @@ def configure(dir=None, format_strs=None, comm=None):
     format_strs = filter(None, format_strs)
     output_formats = [make_output_format(f, dir, log_suffix) for f in format_strs]
 
-    Logger.CURRENT = Logger(dir=dir, output_formats=output_formats, comm=comm)
+    Logger.CURRENT = Logger(dir=dir, output_formats=output_formats)
     log('Logging to %s'%dir)
 
 def _configure_default_logger():
-    configure()
+    format_strs = None
+    # keep the old default of only writing to stdout
+    if 'OPENAI_LOG_FORMAT' not in os.environ:
+        format_strs = ['stdout']
+    configure(format_strs=format_strs)
     Logger.DEFAULT = Logger.CURRENT
 
 def reset():
@@ -404,15 +389,17 @@ def reset():
         Logger.CURRENT = Logger.DEFAULT
         log('Reset logger')
 
-@contextmanager
-def scoped_configure(dir=None, format_strs=None, comm=None):
-    prevlogger = Logger.CURRENT
-    configure(dir=dir, format_strs=format_strs, comm=comm)
-    try:
-        yield
-    finally:
+class scoped_configure(object):
+    def __init__(self, dir=None, format_strs=None):
+        self.dir = dir
+        self.format_strs = format_strs
+        self.prevlogger = None
+    def __enter__(self):
+        self.prevlogger = Logger.CURRENT
+        configure(dir=self.dir, format_strs=self.format_strs)
+    def __exit__(self, *args):
         Logger.CURRENT.close()
-        Logger.CURRENT = prevlogger
+        Logger.CURRENT = self.prevlogger
 
 # ================================================================
 
@@ -436,7 +423,7 @@ def _demo():
     logkv_mean("b", -44.4)
     logkv("a", 5.5)
     dumpkvs()
-    info("^^^ should see b = -33.3")
+    info("^^^ should see b = 33.3")
 
     logkv("b", -2.5)
     dumpkvs()
@@ -469,6 +456,7 @@ def read_tb(path):
     import pandas
     import numpy as np
     from glob import glob
+    from collections import defaultdict
     import tensorflow as tf
     if osp.isdir(path):
         fnames = glob(osp.join(path, "events.*"))
@@ -494,5 +482,8 @@ def read_tb(path):
             data[step-1, colidx] = value
     return pandas.DataFrame(data, columns=tags)
 
+# configure the default logger on import
+_configure_default_logger()
+
 if __name__ == "__main__":
     _demo()

baselines/ppo1/pposgd_simple.py

@@ -97,6 +97,7 @@ def learn(env, policy_fn, *,
     ret = tf.placeholder(dtype=tf.float32, shape=[None]) # Empirical return
 
     lrmult = tf.placeholder(name='lrmult', dtype=tf.float32, shape=[]) # learning rate multiplier, updated with schedule
+    clip_param = clip_param * lrmult # Annealed clipping parameter epsilon
 
     ob = U.get_placeholder_cached(name="ob")
     ac = pi.pdtype.sample_placeholder([None])
@@ -167,7 +168,7 @@ def learn(env, policy_fn, *,
         ob, ac, atarg, tdlamret = seg["ob"], seg["ac"], seg["adv"], seg["tdlamret"]
         vpredbefore = seg["vpred"] # predicted value function before udpate
         atarg = (atarg - atarg.mean()) / atarg.std() # standardized advantage function estimate
-        d = Dataset(dict(ob=ob, ac=ac, atarg=atarg, vtarg=tdlamret), deterministic=pi.recurrent)
+        d = Dataset(dict(ob=ob, ac=ac, atarg=atarg, vtarg=tdlamret), shuffle=not pi.recurrent)
         optim_batchsize = optim_batchsize or ob.shape[0]
 
         if hasattr(pi, "ob_rms"): pi.ob_rms.update(ob) # update running mean/std for policy

baselines/ppo1/run_humanoid.py

@@ -19,17 +19,16 @@ def train(num_timesteps, seed, model_path=None):
     # these are good enough to make humanoid walk, but whether those are
     # an absolute best or not is not certain
     env = RewScale(env, 0.1)
-    logger.log("NOTE: reward will be scaled by a factor of 10  in logged stats. Check the monitor for unscaled reward.")
     pi = pposgd_simple.learn(env, policy_fn,
             max_timesteps=num_timesteps,
             timesteps_per_actorbatch=2048,
-            clip_param=0.1, entcoeff=0.0,
+            clip_param=0.2, entcoeff=0.0,
             optim_epochs=10,
-            optim_stepsize=1e-4,
+            optim_stepsize=3e-4,
             optim_batchsize=64,
             gamma=0.99,
             lam=0.95,
-            schedule='constant',
+            schedule='linear',
         )
     env.close()
     if model_path:
@@ -48,7 +47,7 @@ def main():
     logger.configure()
     parser = mujoco_arg_parser()
     parser.add_argument('--model-path', default=os.path.join(logger.get_dir(), 'humanoid_policy'))
-    parser.set_defaults(num_timesteps=int(5e7))
+    parser.set_defaults(num_timesteps=int(2e7))
 
     args = parser.parse_args()
 
@@ -69,5 +68,8 @@ def main():
             if done:
                 ob = env.reset()
 
+
+
+
 if __name__ == '__main__':
     main()

baselines/ppo2/README.md

@@ -3,16 +3,6 @@
 - Original paper: https://arxiv.org/abs/1707.06347
 - Baselines blog post: https://blog.openai.com/openai-baselines-ppo/
 
-## Examples 
 - `python -m baselines.run --alg=ppo2 --env=PongNoFrameskip-v4` runs the algorithm for 40M frames = 10M timesteps on an Atari Pong. See help (`-h`) for more options.
 - `python -m baselines.run --alg=ppo2 --env=Ant-v2 --num_timesteps=1e6` runs the algorithm for 1M frames on a Mujoco Ant environment.
-
-### RNN networks
-- `python -m baselines.run --alg=ppo2 --env=PongNoFrameskip-v4 --network=ppo_cnn_lstm` runs on an Atari Pong with 
-    `ppo_cnn_lstm` network.
-- `python -m baselines.run --alg=ppo2 --env=Ant-v2 --num_timesteps=1e6 --network=ppo_lstm --value_network=copy` 
-    runs on a Mujoco Ant environment with `ppo_lstm` network whose value and policy networks are separated, but have 
-    same structure.
-
-## See Also
-- refer to the repo-wide [README.md](../../README.md#training-models)
+- also refer to the repo-wide [README.md](../../README.md#training-models)

baselines/ppo2/__init__.py

@@ -1 +0,0 @@
-from baselines.ppo2.layers import ppo_lstm, ppo_cnn_lstm, ppo_cnn_lnlstm  # pylint: disable=unused-import # noqa: F401

baselines/ppo2/defaults.py

@@ -18,7 +18,7 @@ def atari():
         lam=0.95, gamma=0.99, noptepochs=4, log_interval=1,
         ent_coef=.01,
         lr=lambda f : f * 2.5e-4,
-        cliprange=0.1,
+        cliprange=lambda f : f * 0.1,
     )
 
 def retro():

baselines/ppo2/layers.py

@@ -1,55 +0,0 @@
-import numpy as np
-import tensorflow as tf
-
-from baselines.a2c.utils import ortho_init, lstm, lnlstm
-from baselines.common.models import register, nature_cnn
-
-
-class RNN(object):
-    def __init__(self, func, memory_size=None):
-        self._func = func
-        self.memory_size = memory_size
-
-    def __call__(self, *args, **kwargs):
-        return self._func(*args, **kwargs)
-
-
-@register("ppo_lstm")
-def ppo_lstm(num_units=128, layer_norm=False):
-    def network_fn(input, mask, state):
-        input = tf.layers.flatten(input)
-        mask = tf.to_float(mask)
-
-        if layer_norm:
-            h, next_state = lnlstm([input], [mask[:, None]], state, scope='lnlstm', nh=num_units)
-        else:
-            h, next_state = lstm([input], [mask[:, None]], state, scope='lstm', nh=num_units)
-        h = h[0]
-        return h, next_state
-
-    return RNN(network_fn, memory_size=num_units * 2)
-
-
-@register("ppo_cnn_lstm")
-def ppo_cnn_lstm(num_units=128, layer_norm=False, **conv_kwargs):
-    def network_fn(input, mask, state):
-        mask = tf.to_float(mask)
-        initializer = ortho_init(np.sqrt(2))
-
-        h = nature_cnn(input, **conv_kwargs)
-        h = tf.layers.flatten(h)
-        h = tf.layers.dense(h, units=512, activation=tf.nn.relu, kernel_initializer=initializer)
-
-        if layer_norm:
-            h, next_state = lnlstm([h], [mask[:, None]], state, scope='lnlstm', nh=num_units)
-        else:
-            h, next_state = lstm([h], [mask[:, None]], state, scope='lstm', nh=num_units)
-        h = h[0]
-        return h, next_state
-
-    return RNN(network_fn, memory_size=num_units * 2)
-
-
-@register("ppo_cnn_lnlstm")
-def ppo_cnn_lnlstm(num_units=128, **conv_kwargs):
-    return ppo_cnn_lstm(num_units, layer_norm=True, **conv_kwargs)

baselines/ppo2/microbatched_model.py

@@ -1,47 +1,42 @@
-import numpy as np
 import tensorflow as tf
+import numpy as np
 from baselines.ppo2.model import Model
 
-
 class MicrobatchedModel(Model):
     """
     Model that does training one microbatch at a time - when gradient computation
     on the entire minibatch causes some overflow
     """
-
     def __init__(self, *, policy, ob_space, ac_space, nbatch_act, nbatch_train,
-                 nsteps, ent_coef, vf_coef, max_grad_norm, microbatch_size):
+                nsteps, ent_coef, vf_coef, max_grad_norm, microbatch_size):
 
         self.nmicrobatches = nbatch_train // microbatch_size
         self.microbatch_size = microbatch_size
-        assert nbatch_train % microbatch_size == 0, 'microbatch_size ({}) should divide nbatch_train ({}) evenly'.format(
-            microbatch_size, nbatch_train)
+        assert nbatch_train % microbatch_size == 0, 'microbatch_size ({}) should divide nbatch_train ({}) evenly'.format(microbatch_size, nbatch_train)
 
         super().__init__(
-            policy=policy,
-            ob_space=ob_space,
-            ac_space=ac_space,
-            nbatch_act=nbatch_act,
-            nbatch_train=microbatch_size,
-            nsteps=nsteps,
-            ent_coef=ent_coef,
-            vf_coef=vf_coef,
-            max_grad_norm=max_grad_norm)
+                policy=policy,
+                ob_space=ob_space,
+                ac_space=ac_space,
+                nbatch_act=nbatch_act,
+                nbatch_train=microbatch_size,
+                nsteps=nsteps,
+                ent_coef=ent_coef,
+                vf_coef=vf_coef,
+                max_grad_norm=max_grad_norm)
 
         self.grads_ph = [tf.placeholder(dtype=g.dtype, shape=g.shape) for g in self.grads]
         grads_ph_and_vars = list(zip(self.grads_ph, self.var))
         self._apply_gradients_op = self.trainer.apply_gradients(grads_ph_and_vars)
 
-    def train(self,
-              lr,
-              cliprange,
-              observations,
-              advs,
-              returns,
-              actions,
-              values,
-              neglogpacs,
-              **_kwargs):
+
+    def train(self, lr, cliprange, obs, returns, masks, actions, values, neglogpacs, states=None):
+        assert states is None, "microbatches with recurrent models are not supported yet"
+
+        # Here we calculate advantage A(s,a) = R + yV(s') - V(s)
+        # Returns = R + yV(s')
+        advs = returns - values
+
         # Normalize the advantages
         advs = (advs - advs.mean()) / (advs.std() + 1e-8)
 
@@ -49,24 +44,19 @@ class MicrobatchedModel(Model):
         stats_vs = []
 
         for microbatch_idx in range(self.nmicrobatches):
-            _sli = range(microbatch_idx * self.microbatch_size, (microbatch_idx + 1) * self.microbatch_size)
-
+            _sli = range(microbatch_idx * self.microbatch_size, (microbatch_idx+1) * self.microbatch_size)
             td_map = {
-                self.train_model.X: observations[_sli],
-                self.A: actions[_sli],
-                self.ADV: advs[_sli],
-                self.RETURNS: returns[_sli],
-                self.LR: lr,
-                self.CLIPRANGE: cliprange,
-                self.OLDNEGLOGPAC: neglogpacs[_sli],
-                self.VALUE_PREV: values[_sli],
+                self.train_model.X: obs[_sli],
+                self.A:actions[_sli],
+                self.ADV:advs[_sli],
+                self.R:returns[_sli],
+                self.CLIPRANGE:cliprange,
+                self.OLDNEGLOGPAC:neglogpacs[_sli],
+                self.OLDVPRED:values[_sli]
             }
 
-            sliced_kwargs = {key: _kwargs[key][_sli] for key in _kwargs}
-            td_map.update(self.train_model.feed_dict(**sliced_kwargs))
-
             # Compute gradient on a microbatch (note that variables do not change here) ...
-            grad_v, stats_v = self.sess.run([self.grads, self.stats_list], td_map)
+            grad_v, stats_v  = self.sess.run([self.grads, self.stats_list], td_map)
             if microbatch_idx == 0:
                 sum_grad_v = grad_v
             else:
@@ -81,3 +71,6 @@ class MicrobatchedModel(Model):
         self.sess.run(self._apply_gradients_op, feed_dict)
         # Return average of the stats
         return np.mean(np.array(stats_vs), axis=0).tolist()
+
+
+

baselines/ppo2/model.py

@@ -1,8 +1,8 @@
+import tensorflow as tf
 import functools
 
-import tensorflow as tf
-
 from baselines.common.tf_util import get_session, save_variables, load_variables
+from baselines.common.tf_util import initialize
 
 try:
     from baselines.common.mpi_adam_optimizer import MpiAdamOptimizer
@@ -11,7 +11,6 @@ try:
 except ImportError:
     MPI = None
 
-
 class Model(object):
     """
     We use this object to :
@@ -25,157 +24,133 @@ class Model(object):
     save/load():
     - Save load the model
     """
-
     def __init__(self, *, policy, ob_space, ac_space, nbatch_act, nbatch_train,
-                 nsteps, ent_coef, vf_coef, max_grad_norm,
-                 name='ppo_model',
-                 sess=None,
-                 microbatch_size=None):
-        if sess is None:
-            sess = get_session()
-        self.sess = sess
-        self.name = name
+                nsteps, ent_coef, vf_coef, max_grad_norm, microbatch_size=None):
+        self.sess = sess = get_session()
 
-        with tf.variable_scope(name) as scope:
-            self.scope = scope
-            with tf.variable_scope('models', reuse=tf.AUTO_REUSE):
-                with tf.name_scope('act_model'):
-                    # CREATE OUR TWO MODELS
-                    # act_model that is used for sampling
-                    act_model = policy(nbatch_act, 1, sess)
+        with tf.variable_scope('ppo2_model', reuse=tf.AUTO_REUSE):
+            # CREATE OUR TWO MODELS
+            # act_model that is used for sampling
+            act_model = policy(nbatch_act, 1, sess)
 
-                with tf.name_scope('train_model'):
-                    # Train model for training
-                    if microbatch_size is None:
-                        train_model = policy(nbatch_train, nsteps, sess)
-                    else:
-                        train_model = policy(microbatch_size, nsteps, sess)
+            # Train model for training
+            if microbatch_size is None:
+                train_model = policy(nbatch_train, nsteps, sess)
+            else:
+                train_model = policy(microbatch_size, nsteps, sess)
 
-            with tf.variable_scope('losses'):
-                # CREATE THE PLACEHOLDERS
-                self.A = A = train_model.pdtype.sample_placeholder([None], name='action')
-                self.ADV = ADV = tf.placeholder(tf.float32, [None], name='advantage')
-                self.RETURNS = RETURNS = tf.placeholder(tf.float32, [None], name='reward')
-                self.VALUE_PREV = VALUE_PREV = tf.placeholder(tf.float32, [None], name='value_prev')
-                self.OLDNEGLOGPAC = OLDNEGLOGPAC = tf.placeholder(tf.float32, [None],
-                                                                  name='negative_log_p_action_old')
-                self.CLIPRANGE = CLIPRANGE = tf.placeholder(tf.float32, [], name='clip_range')
+        # CREATE THE PLACEHOLDERS
+        self.A = A = train_model.pdtype.sample_placeholder([None])
+        self.ADV = ADV = tf.placeholder(tf.float32, [None])
+        self.R = R = tf.placeholder(tf.float32, [None])
+        # Keep track of old actor
+        self.OLDNEGLOGPAC = OLDNEGLOGPAC = tf.placeholder(tf.float32, [None])
+        # Keep track of old critic
+        self.OLDVPRED = OLDVPRED = tf.placeholder(tf.float32, [None])
+        self.LR = LR = tf.placeholder(tf.float32, [])
+        # Cliprange
+        self.CLIPRANGE = CLIPRANGE = tf.placeholder(tf.float32, [])
 
-                with tf.name_scope("neglogpac"):
-                    neglogpac = train_model.pd.neglogp(A)
+        neglogpac = train_model.pd.neglogp(A)
 
-                with tf.name_scope("entropy"):
-                    # Calculate the entropy
-                    # Entropy is used to improve exploration by limiting the premature convergence to suboptimal policy.
-                    entropy = tf.reduce_mean(train_model.pd.entropy())
-                    entropy_loss = (- ent_coef) * entropy
+        # Calculate the entropy
+        # Entropy is used to improve exploration by limiting the premature convergence to suboptimal policy.
+        entropy = tf.reduce_mean(train_model.pd.entropy())
 
-                with tf.name_scope("value_loss"):
-                    # CALCULATE THE LOSS
-                    value = train_model.value
-                    value_clipped = VALUE_PREV + tf.clip_by_value(value - VALUE_PREV, -CLIPRANGE, CLIPRANGE)
-                    vf_losses1 = tf.squared_difference(value, RETURNS)
-                    vf_losses2 = tf.squared_difference(value_clipped, RETURNS)
-                    vf_loss = 0.5 * vf_coef * tf.reduce_mean(tf.maximum(vf_losses1, vf_losses2))
+        # CALCULATE THE LOSS
+        # Total loss = Policy gradient loss - entropy * entropy coefficient + Value coefficient * value loss
 
-                with tf.name_scope("policy_loss"):
-                    # Calculate ratio (pi current policy / pi old policy)
-                    ratio = tf.exp(OLDNEGLOGPAC - neglogpac)
-                    pg_losses = -ADV * ratio
-                    pg_losses2 = -ADV * tf.clip_by_value(ratio, 1.0 - CLIPRANGE, 1.0 + CLIPRANGE)
-                    pg_loss = tf.reduce_mean(tf.maximum(pg_losses, pg_losses2))
+        # Clip the value to reduce variability during Critic training
+        # Get the predicted value
+        vpred = train_model.vf
+        vpredclipped = OLDVPRED + tf.clip_by_value(train_model.vf - OLDVPRED, - CLIPRANGE, CLIPRANGE)
+        # Unclipped value
+        vf_losses1 = tf.square(vpred - R)
+        # Clipped value
+        vf_losses2 = tf.square(vpredclipped - R)
 
-                with tf.name_scope("approxkl"):
-                    approxkl = .5 * tf.reduce_mean(tf.squared_difference(neglogpac, OLDNEGLOGPAC))
+        vf_loss = .5 * tf.reduce_mean(tf.maximum(vf_losses1, vf_losses2))
 
-                with tf.name_scope("clip_fraction"):
-                    clipfrac = tf.reduce_mean(tf.to_float(tf.greater(tf.abs(ratio - 1.0), CLIPRANGE)))
+        # Calculate ratio (pi current policy / pi old policy)
+        ratio = tf.exp(OLDNEGLOGPAC - neglogpac)
 
-                with tf.name_scope("total_loss"):
-                    loss = pg_loss + entropy_loss + vf_loss
+        # Defining Loss = - J is equivalent to max J
+        pg_losses = -ADV * ratio
 
-            with tf.variable_scope('optimizer'):
-                self.LR = LR = tf.placeholder(tf.float32, [], name='learning_rate')
+        pg_losses2 = -ADV * tf.clip_by_value(ratio, 1.0 - CLIPRANGE, 1.0 + CLIPRANGE)
 
-                # UPDATE THE PARAMETERS USING LOSS
-                # 1. Get the model parameters
-                params = tf.trainable_variables(self.scope.name)
+        # Final PG loss
+        pg_loss = tf.reduce_mean(tf.maximum(pg_losses, pg_losses2))
+        approxkl = .5 * tf.reduce_mean(tf.square(neglogpac - OLDNEGLOGPAC))
+        clipfrac = tf.reduce_mean(tf.to_float(tf.greater(tf.abs(ratio - 1.0), CLIPRANGE)))
 
-                # 2. Build our trainer
-                if MPI is not None:
-                    self.trainer = MpiAdamOptimizer(MPI.COMM_WORLD, learning_rate=LR, epsilon=1e-5)
-                else:
-                    self.trainer = tf.train.AdamOptimizer(learning_rate=LR, epsilon=1e-5)
-                # 3. Calculate the gradients
-                grads_and_var = self.trainer.compute_gradients(loss, params)
-                grads, var = zip(*grads_and_var)
+        # Total loss
+        loss = pg_loss - entropy * ent_coef + vf_loss * vf_coef
 
-                if max_grad_norm is not None:
-                    # Clip the gradients (normalize)
-                    grads, _grad_norm = tf.clip_by_global_norm(grads, max_grad_norm)
-                grads_and_var = list(zip(grads, var))
+        # UPDATE THE PARAMETERS USING LOSS
+        # 1. Get the model parameters
+        params = tf.trainable_variables('ppo2_model')
+        # 2. Build our trainer
+        if MPI is not None:
+            self.trainer = MpiAdamOptimizer(MPI.COMM_WORLD, learning_rate=LR, epsilon=1e-5)
+        else:
+            self.trainer = tf.train.AdamOptimizer(learning_rate=LR, epsilon=1e-5)
+        # 3. Calculate the gradients
+        grads_and_var = self.trainer.compute_gradients(loss, params)
+        grads, var = zip(*grads_and_var)
 
-                self.grads = grads
-                self.var = var
-                self._train_op = self.trainer.apply_gradients(grads_and_var)
+        if max_grad_norm is not None:
+            # Clip the gradients (normalize)
+            grads, _grad_norm = tf.clip_by_global_norm(grads, max_grad_norm)
+        grads_and_var = list(zip(grads, var))
+        # zip aggregate each gradient with parameters associated
+        # For instance zip(ABCD, xyza) => Ax, By, Cz, Da
 
-                self.loss_names = ['policy_loss', 'value_loss', 'entropy_loss', 'approxkl', 'clipfrac',
-                                   'total_loss']
-                self.stats_list = [pg_loss, vf_loss, entropy_loss, approxkl, clipfrac, loss]
+        self.grads = grads
+        self.var = var
+        self._train_op = self.trainer.apply_gradients(grads_and_var)
+        self.loss_names = ['policy_loss', 'value_loss', 'policy_entropy', 'approxkl', 'clipfrac']
+        self.stats_list = [pg_loss, vf_loss, entropy, approxkl, clipfrac]
 
-                self.train_model = train_model
-                self.act_model = act_model
-                self.initial_state = act_model.initial_state
 
-                self.save = functools.partial(save_variables, sess=sess)
-                self.load = functools.partial(load_variables, sess=sess)
+        self.train_model = train_model
+        self.act_model = act_model
+        self.step = act_model.step
+        self.value = act_model.value
+        self.initial_state = act_model.initial_state
 
-            with tf.variable_scope('initialization'):
-                sess.run(tf.initializers.variables(tf.global_variables(self.scope.name)))
-                sess.run(tf.initializers.variables(tf.local_variables(self.scope.name)))
-                global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope=self.scope.name)
-                if MPI is not None:
-                    sync_from_root(sess, global_variables)  # pylint: disable=E1101
+        self.save = functools.partial(save_variables, sess=sess)
+        self.load = functools.partial(load_variables, sess=sess)
 
-    def step_with_dict(self, **kwargs):
-        return self.act_model.step(**kwargs)
+        initialize()
+        global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="")
+        if MPI is not None:
+            sync_from_root(sess, global_variables) #pylint: disable=E1101
 
-    def step(self, obs, M=None, S=None, **kwargs):
-        kwargs.update({'observations': obs})
-        if M is not None and S is not None:
-            kwargs.update({'dones': M})
-            kwargs.update({'states': S})
-        transition = self.act_model.step(**kwargs)
-        states = transition['next_states'] if 'next_states' in transition else None
-        return transition['actions'], transition['values'], states, transition['neglogpacs']
+    def train(self, lr, cliprange, obs, returns, masks, actions, values, neglogpacs, states=None):
+        # Here we calculate advantage A(s,a) = R + yV(s') - V(s)
+        # Returns = R + yV(s')
+        advs = returns - values
 
-    def train(self,
-              lr,
-              cliprange,
-              observations,
-              advs,
-              returns,
-              actions,
-              values,
-              neglogpacs,
-              **_kwargs):
         # Normalize the advantages
         advs = (advs - advs.mean()) / (advs.std() + 1e-8)
 
         td_map = {
-            self.train_model.X: observations,
-            self.A: actions,
-            self.ADV: advs,
-            self.RETURNS: returns,
-            self.LR: lr,
-            self.CLIPRANGE: cliprange,
-            self.OLDNEGLOGPAC: neglogpacs,
-            self.VALUE_PREV: values,
+            self.train_model.X : obs,
+            self.A : actions,
+            self.ADV : advs,
+            self.R : returns,
+            self.LR : lr,
+            self.CLIPRANGE : cliprange,
+            self.OLDNEGLOGPAC : neglogpacs,
+            self.OLDVPRED : values
         }
-
-        td_map.update(self.train_model.feed_dict(**_kwargs))
+        if states is not None:
+            td_map[self.train_model.S] = states
+            td_map[self.train_model.M] = masks
 
         return self.sess.run(
             self.stats_list + [self._train_op],
             td_map
         )[:-1]
+

baselines/ppo2/policies.py

@@ -1,188 +0,0 @@
-import gym
-import numpy as np
-import tensorflow as tf
-
-from baselines.a2c.utils import fc
-from baselines.common import tf_util
-from baselines.common.distributions import make_pdtype
-from baselines.common.input import observation_placeholder, encode_observation
-from baselines.common.models import get_network_builder
-from baselines.common.tf_util import adjust_shape
-from baselines.ppo2.layers import RNN
-
-
-class PolicyWithValue(object):
-    """
-    Encapsulates fields and methods for RL policy and two value function estimation with shared parameters
-    """
-
-    def __init__(self, env, observations, latent, dones, states=None, estimate_q=False, vf_latent=None, sess=None):
-        """
-        Parameters:
-        ----------
-        env             RL environment
-
-        observations    tensorflow placeholder in which the observations will be fed
-
-        latent          latent state from which policy distribution parameters should be inferred
-
-        vf_latent       latent state from which value function should be inferred (if None, then latent is used)
-
-        sess            tensorflow session to run calculations in (if None, default session is used)
-
-        **tensors       tensorflow tensors for additional attributes such as state or mask
-
-        """
-        self.X = observations
-        self.dones = dones
-        self.pdtype = make_pdtype(env.action_space)
-        self.states = states
-        self.sess = sess or tf.get_default_session()
-
-        vf_latent = vf_latent if vf_latent is not None else latent
-
-        with tf.variable_scope('policy'):
-            latent = tf.layers.flatten(latent)
-            # Based on the action space, will select what probability distribution type
-            self.pd, self.pi = self.pdtype.pdfromlatent(latent, init_scale=0.01)
-
-            with tf.variable_scope('sample_action'):
-                self.action = self.pd.sample()
-
-            with tf.variable_scope('negative_log_probability'):
-                # Calculate the neg log of our probability
-                self.neglogp = self.pd.neglogp(self.action)
-
-        with tf.variable_scope('value'):
-            vf_latent = tf.layers.flatten(vf_latent)
-
-            if estimate_q:
-                assert isinstance(env.action_space, gym.spaces.Discrete)
-                self.q = fc(vf_latent, 'q', env.action_space.n)
-                self.value = self.q
-            else:
-                vf_latent = tf.layers.flatten(vf_latent)
-                self.value = fc(vf_latent, 'value', 1, init_scale=0.01)
-                self.value = self.value[:, 0]
-
-        self.step_input = {
-            'observations': observations,
-            'dones': self.dones,
-        }
-
-        self.step_output = {
-            'actions': self.action,
-            'values': self.value,
-            'neglogpacs': self.neglogp,
-        }
-        if self.states:
-            self.initial_state = np.zeros(self.states['current'].get_shape())
-            self.step_input.update({'states': self.states['current']})
-            self.step_output.update({'states': self.states['current'],
-                                     'next_states': self.states['next']})
-        else:
-            self.initial_state = None
-
-    def feed_dict(self, **kwargs):
-        feed_dict = {}
-        for key in kwargs:
-            if key in self.step_input:
-                feed_dict[self.step_input[key]] = adjust_shape(self.step_input[key], kwargs[key])
-        return feed_dict
-
-    def step(self, **kwargs):
-        return self.sess.run(self.step_output,
-                             feed_dict=self.feed_dict(**kwargs))
-
-    def values(self, **kwargs):
-        return self.sess.run({'values': self.value},
-                             feed_dict=self.feed_dict(**kwargs))
-
-    def save(self, save_path):
-        tf_util.save_state(save_path, sess=self.sess)
-
-    def load(self, load_path):
-        tf_util.load_state(load_path, sess=self.sess)
-
-
-def build_ppo_policy(env, policy_network, value_network=None, estimate_q=False, **policy_kwargs):
-    if isinstance(policy_network, str):
-        network_type = policy_network
-        policy_network = get_network_builder(network_type)(**policy_kwargs)
-
-    if value_network is None:
-        value_network = 'shared'
-
-    def policy_fn(nbatch=None, nsteps=None, sess=None, observ_placeholder=None):
-        next_states_list = []
-        state_map = {}
-        state_placeholder = None
-
-        ob_space = env.observation_space
-        X = observ_placeholder if observ_placeholder is not None else observation_placeholder(ob_space,
-                                                                                              batch_size=nbatch)
-        dones = tf.placeholder(tf.float32, shape=[X.shape[0]], name='dones')
-        encoded_x = encode_observation(ob_space, X)
-
-        with tf.variable_scope('current_rnn_memory'):
-            if value_network == 'shared':
-                value_network_ = value_network
-            else:
-                if value_network == 'copy':
-                    value_network_ = policy_network
-                else:
-                    assert callable(value_network)
-                    value_network_ = value_network
-
-            policy_memory_size = policy_network.memory_size if isinstance(policy_network, RNN) else 0
-            value_memory_size = value_network_.memory_size if isinstance(value_network_, RNN) else 0
-            state_size = policy_memory_size + value_memory_size
-
-            if state_size > 0:
-                state_placeholder = tf.placeholder(dtype=tf.float32, shape=(nbatch, state_size),
-                                                   name='states')
-
-                state_map['policy'] = state_placeholder[:, 0:policy_memory_size]
-                state_map['value'] = state_placeholder[:, policy_memory_size:]
-
-        with tf.variable_scope('policy_latent', reuse=tf.AUTO_REUSE):
-            if isinstance(policy_network, RNN):
-                assert policy_memory_size > 0
-                policy_latent, next_policy_state = \
-                    policy_network(encoded_x, dones, state_map['policy'])
-                next_states_list.append(next_policy_state)
-            else:
-                policy_latent = policy_network(encoded_x)
-
-        with tf.variable_scope('value_latent', reuse=tf.AUTO_REUSE):
-            if value_network_ == 'shared':
-                value_latent = policy_latent
-            elif isinstance(value_network_, RNN):
-                assert value_memory_size > 0
-                value_latent, next_value_state = \
-                    value_network_(encoded_x, dones, state_map['value'])
-                next_states_list.append(next_value_state)
-            else:
-                value_latent = value_network_(encoded_x)
-
-        with tf.name_scope("next_rnn_memory"):
-            if state_size > 0:
-                next_states = tf.concat(next_states_list, axis=1)
-                state_info = {'current': state_placeholder,
-                              'next': next_states, }
-            else:
-                state_info = None
-
-        policy = PolicyWithValue(
-            env=env,
-            observations=X,
-            dones=dones,
-            latent=policy_latent,
-            vf_latent=value_latent,
-            states=state_info,
-            sess=sess,
-            estimate_q=estimate_q,
-        )
-        return policy
-
-    return policy_fn

baselines/ppo2/ppo2.py

@@ -1,35 +1,28 @@
 import os
-import os.path as osp
 import time
-from collections import deque
-
 import numpy as np
-import tensorflow as tf
+import os.path as osp
 from baselines import logger
-from baselines.common import explained_variance
-from baselines.common import set_global_seeds
-from baselines.common.tf_util import display_var_info
-from baselines.ppo2.policies import build_ppo_policy
-from baselines.ppo2.runner import Runner
-
+from collections import deque
+from baselines.common import explained_variance, set_global_seeds
+from baselines.common.policies import build_policy
 try:
     from mpi4py import MPI
 except ImportError:
     MPI = None
+from baselines.ppo2.runner import Runner
 
 
 def constfn(val):
     def f(_):
         return val
-
     return f
 
-
-def learn(*, network, env, total_timesteps, eval_env=None, seed=None, nsteps=128, ent_coef=0.0, lr=3e-4,
-          vf_coef=0.5, max_grad_norm=0.5, gamma=0.99, lam=0.95,
-          log_interval=10, nminibatches=4, noptepochs=4, cliprange=0.2,
-          save_interval=10, load_path=None, model_fn=None, **network_kwargs):
-    """
+def learn(*, network, env, total_timesteps, eval_env = None, seed=None, nsteps=2048, ent_coef=0.0, lr=3e-4,
+            vf_coef=0.5,  max_grad_norm=0.5, gamma=0.99, lam=0.95,
+            log_interval=10, nminibatches=4, noptepochs=4, cliprange=0.2,
+            save_interval=0, load_path=None, model_fn=None, **network_kwargs):
+    '''
     Learn policy using PPO algorithm (https://arxiv.org/abs/1707.06347)
 
     Parameters:
@@ -59,7 +52,7 @@ def learn(*, network, env, total_timesteps, eval_env=None, seed=None, nsteps=128
 
     max_grad_norm: float or None      gradient norm clipping coefficient
 
-    gamma: float                      discounting factor for rewards
+    gamma: float                      discounting factor
 
     lam: float                        advantage estimation discounting factor (lambda in the paper)
 
@@ -79,21 +72,20 @@ def learn(*, network, env, total_timesteps, eval_env=None, seed=None, nsteps=128
 
     **network_kwargs:                 keyword arguments to the policy / network builder. See baselines.common/policies.py/build_policy and arguments to a particular type of network
                                       For instance, 'mlp' network architecture has arguments num_hidden and num_layers.
-    """
+
+
+
+    '''
 
     set_global_seeds(seed)
 
-    if isinstance(lr, float):
-        lr = constfn(lr)
-    else:
-        assert callable(lr)
-    if isinstance(cliprange, float):
-        cliprange = constfn(cliprange)
-    else:
-        assert callable(cliprange)
+    if isinstance(lr, float): lr = constfn(lr)
+    else: assert callable(lr)
+    if isinstance(cliprange, float): cliprange = constfn(cliprange)
+    else: assert callable(cliprange)
     total_timesteps = int(total_timesteps)
 
-    policy = build_ppo_policy(env, network, **network_kwargs)
+    policy = build_policy(env, network, **network_kwargs)
 
     # Get the nb of env
     nenvs = env.num_envs
@@ -112,111 +104,108 @@ def learn(*, network, env, total_timesteps, eval_env=None, seed=None, nsteps=128
         model_fn = Model
 
     model = model_fn(policy=policy, ob_space=ob_space, ac_space=ac_space, nbatch_act=nenvs, nbatch_train=nbatch_train,
-                     nsteps=nsteps, ent_coef=ent_coef, vf_coef=vf_coef, max_grad_norm=max_grad_norm)
+                    nsteps=nsteps, ent_coef=ent_coef, vf_coef=vf_coef,
+                    max_grad_norm=max_grad_norm)
 
     if load_path is not None:
         model.load(load_path)
-
-    allvars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope=model.name)
-    display_var_info(allvars)
-
     # Instantiate the runner object
-    runner = Runner(env=env, model=model, nsteps=nsteps, gamma=gamma, ob_space=ob_space, lam=lam)
-
+    runner = Runner(env=env, model=model, nsteps=nsteps, gamma=gamma, lam=lam)
     if eval_env is not None:
-        eval_runner = Runner(env=eval_env, model=model, nsteps=nsteps, gamma=gamma, ob_space=ob_space, lam=lam)
+        eval_runner = Runner(env = eval_env, model = model, nsteps = nsteps, gamma = gamma, lam= lam)
 
     epinfobuf = deque(maxlen=100)
     if eval_env is not None:
         eval_epinfobuf = deque(maxlen=100)
 
     # Start total timer
-    tfirststart = time.perf_counter()
-    nupdates = total_timesteps // nbatch
+    tfirststart = time.time()
 
-    for update in range(1, nupdates + 1):
+    nupdates = total_timesteps//nbatch
+    for update in range(1, nupdates+1):
         assert nbatch % nminibatches == 0
         # Start timer
-        tstart = time.perf_counter()
+        tstart = time.time()
         frac = 1.0 - (update - 1.0) / nupdates
         # Calculate the learning rate
         lrnow = lr(frac)
         # Calculate the cliprange
         cliprangenow = cliprange(frac)
-
         # Get minibatch
-        minibatch = runner.run()
-
+        obs, returns, masks, actions, values, neglogpacs, states, epinfos = runner.run() #pylint: disable=E0632
         if eval_env is not None:
-            eval_minibatch = eval_runner.run()
-            _eval_obs = eval_minibatch['observations']  # noqa: F841
-            _eval_returns = eval_minibatch['returns']   # noqa: F841
-            _eval_masks = eval_minibatch['masks']       # noqa: F841
-            _eval_actions = eval_minibatch['actions']   # noqa: F841
-            _eval_values = eval_minibatch['values']     # noqa: F841
-            _eval_neglogpacs = eval_minibatch['neglogpacs'] # noqa: F841
-            _eval_states = eval_minibatch['state']      # noqa: F841
-            eval_epinfos = eval_minibatch['epinfos']
+            eval_obs, eval_returns, eval_masks, eval_actions, eval_values, eval_neglogpacs, eval_states, eval_epinfos = eval_runner.run() #pylint: disable=E0632
 
-        epinfobuf.extend(minibatch.pop('epinfos'))
+        epinfobuf.extend(epinfos)
         if eval_env is not None:
             eval_epinfobuf.extend(eval_epinfos)
 
         # Here what we're going to do is for each minibatch calculate the loss and append it.
         mblossvals = []
-
-        # Index of each element of batch_size
-        # Create the indices array
-        inds = np.arange(nbatch)
-        for _ in range(noptepochs):
-            # Randomize the indexes
-            np.random.shuffle(inds)
-            # 0 to batch_size with batch_train_size step
-            for start in range(0, nbatch, nbatch_train):
-                end = start + nbatch_train
-                mbinds = inds[start:end]
-                slices = {key: minibatch[key][mbinds] for key in minibatch}
-                mblossvals.append(model.train(lrnow, cliprangenow, **slices))
+        if states is None: # nonrecurrent version
+            # Index of each element of batch_size
+            # Create the indices array
+            inds = np.arange(nbatch)
+            for _ in range(noptepochs):
+                # Randomize the indexes
+                np.random.shuffle(inds)
+                # 0 to batch_size with batch_train_size step
+                for start in range(0, nbatch, nbatch_train):
+                    end = start + nbatch_train
+                    mbinds = inds[start:end]
+                    slices = (arr[mbinds] for arr in (obs, returns, masks, actions, values, neglogpacs))
+                    mblossvals.append(model.train(lrnow, cliprangenow, *slices))
+        else: # recurrent version
+            assert nenvs % nminibatches == 0
+            envsperbatch = nenvs // nminibatches
+            envinds = np.arange(nenvs)
+            flatinds = np.arange(nenvs * nsteps).reshape(nenvs, nsteps)
+            envsperbatch = nbatch_train // nsteps
+            for _ in range(noptepochs):
+                np.random.shuffle(envinds)
+                for start in range(0, nenvs, envsperbatch):
+                    end = start + envsperbatch
+                    mbenvinds = envinds[start:end]
+                    mbflatinds = flatinds[mbenvinds].ravel()
+                    slices = (arr[mbflatinds] for arr in (obs, returns, masks, actions, values, neglogpacs))
+                    mbstates = states[mbenvinds]
+                    mblossvals.append(model.train(lrnow, cliprangenow, *slices, mbstates))
 
         # Feedforward --> get losses --> update
         lossvals = np.mean(mblossvals, axis=0)
         # End timer
-        tnow = time.perf_counter()
+        tnow = time.time()
         # Calculate the fps (frame per second)
         fps = int(nbatch / (tnow - tstart))
         if update % log_interval == 0 or update == 1:
             # Calculates if value function is a good predicator of the returns (ev > 1)
             # or if it's just worse than predicting nothing (ev =< 0)
-            ev = explained_variance(minibatch['values'], minibatch['returns'])
-            logger.logkv("serial_timesteps", update * nsteps)
+            ev = explained_variance(values, returns)
+            logger.logkv("serial_timesteps", update*nsteps)
             logger.logkv("nupdates", update)
-            logger.logkv("total_timesteps", update * nbatch)
+            logger.logkv("total_timesteps", update*nbatch)
             logger.logkv("fps", fps)
             logger.logkv("explained_variance", float(ev))
             logger.logkv('eprewmean', safemean([epinfo['r'] for epinfo in epinfobuf]))
             logger.logkv('eplenmean', safemean([epinfo['l'] for epinfo in epinfobuf]))
-            logger.logkv('rewards_per_step', safemean(minibatch['rewards']))
-            logger.logkv('advantages_per_step', safemean(minibatch['advs']))
-
             if eval_env is not None:
-                logger.logkv('eval_eprewmean', safemean([epinfo['r'] for epinfo in eval_epinfobuf]))
-                logger.logkv('eval_eplenmean', safemean([epinfo['l'] for epinfo in eval_epinfobuf]))
+                logger.logkv('eval_eprewmean', safemean([epinfo['r'] for epinfo in eval_epinfobuf]) )
+                logger.logkv('eval_eplenmean', safemean([epinfo['l'] for epinfo in eval_epinfobuf]) )
             logger.logkv('time_elapsed', tnow - tfirststart)
             for (lossval, lossname) in zip(lossvals, model.loss_names):
                 logger.logkv(lossname, lossval)
             if MPI is None or MPI.COMM_WORLD.Get_rank() == 0:
                 logger.dumpkvs()
-        if save_interval and (update % save_interval == 0 or update == 1) and logger.get_dir() and (
-            MPI is None or MPI.COMM_WORLD.Get_rank() == 0):
+        if save_interval and (update % save_interval == 0 or update == 1) and logger.get_dir() and (MPI is None or MPI.COMM_WORLD.Get_rank() == 0):
             checkdir = osp.join(logger.get_dir(), 'checkpoints')
             os.makedirs(checkdir, exist_ok=True)
-            savepath = osp.join(checkdir, '%.5i' % update)
+            savepath = osp.join(checkdir, '%.5i'%update)
             print('Saving to', savepath)
             model.save(savepath)
-        del minibatch
     return model
-
-
 # Avoid division error when calculate the mean (in our case if epinfo is empty returns np.nan, not return an error)
 def safemean(xs):
     return np.nan if len(xs) == 0 else np.mean(xs)
+
+
+

baselines/ppo2/runner.py

@@ -1,8 +1,6 @@
 import numpy as np
-
 from baselines.common.runners import AbstractEnvRunner
 
-
 class Runner(AbstractEnvRunner):
     """
     We use this object to make a mini batch of experiences
@@ -12,118 +10,67 @@ class Runner(AbstractEnvRunner):
     run():
     - Make a mini batch
     """
-
-    def __init__(self, *, env, model, nsteps, gamma, ob_space, lam):
+    def __init__(self, *, env, model, nsteps, gamma, lam):
         super().__init__(env=env, model=model, nsteps=nsteps)
-
-        self.lam = lam  # Lambda used in GAE (General Advantage Estimation)
-        self.gamma = gamma  # Discount rate for rewards
-        self.ob_space = ob_space
+        # Lambda used in GAE (General Advantage Estimation)
+        self.lam = lam
+        # Discount rate
+        self.gamma = gamma
 
     def run(self):
-        minibatch = {
-            "observations": [],
-            "actions": [],
-            "rewards": [],
-            "values": [],
-            "dones": [],
-            "neglogpacs": [],
-        }
-
-        data_type = {
-            "observations": self.obs.dtype,
-            "actions": np.float32,
-            "rewards": np.float32,
-            "values": np.float32,
-            "dones": np.float32,
-            "neglogpacs": np.float32,
-        }
-
-        prev_transition = {'next_states': self.model.initial_state} if self.model.initial_state is not None else {}
+        # Here, we init the lists that will contain the mb of experiences
+        mb_obs, mb_rewards, mb_actions, mb_values, mb_dones, mb_neglogpacs = [],[],[],[],[],[]
+        mb_states = self.states
         epinfos = []
-
         # For n in range number of steps
         for _ in range(self.nsteps):
-            transitions = {}
-            transitions['observations'] = self.obs.copy()
-            transitions['dones'] = self.dones
-            if 'next_states' in prev_transition:
-                transitions['states'] = prev_transition['next_states']
-            transitions.update(self.model.step_with_dict(**transitions))
+            # Given observations, get action value and neglopacs
+            # We already have self.obs because Runner superclass run self.obs[:] = env.reset() on init
+            actions, values, self.states, neglogpacs = self.model.step(self.obs, S=self.states, M=self.dones)
+            mb_obs.append(self.obs.copy())
+            mb_actions.append(actions)
+            mb_values.append(values)
+            mb_neglogpacs.append(neglogpacs)
+            mb_dones.append(self.dones)
 
             # Take actions in env and look the results
             # Infos contains a ton of useful informations
-            self.obs, transitions['rewards'], self.dones, infos = self.env.step(transitions['actions'])
-            self.dones = np.array(self.dones, dtype=np.float)
-
+            self.obs[:], rewards, self.dones, infos = self.env.step(actions)
             for info in infos:
                 maybeepinfo = info.get('episode')
-                if maybeepinfo:
-                    epinfos.append(maybeepinfo)
+                if maybeepinfo: epinfos.append(maybeepinfo)
+            mb_rewards.append(rewards)
+        #batch of steps to batch of rollouts
+        mb_obs = np.asarray(mb_obs, dtype=self.obs.dtype)
+        mb_rewards = np.asarray(mb_rewards, dtype=np.float32)
+        mb_actions = np.asarray(mb_actions)
+        mb_values = np.asarray(mb_values, dtype=np.float32)
+        mb_neglogpacs = np.asarray(mb_neglogpacs, dtype=np.float32)
+        mb_dones = np.asarray(mb_dones, dtype=np.bool)
+        last_values = self.model.value(self.obs, S=self.states, M=self.dones)
 
-            for key in transitions:
-                if key not in minibatch:
-                    minibatch[key] = []
-                minibatch[key].append(transitions[key])
-            prev_transition = transitions
-
-        for key in minibatch:
-            dtype = data_type[key] if key in data_type else np.float
-            minibatch[key] = np.array(minibatch[key], dtype=dtype)
-
-        transitions['observations'] = self.obs.copy()
-        transitions['dones'] = self.dones
-        if 'states' in transitions:
-            transitions['states'] = transitions.pop('next_states')
-
-        for key in minibatch:
-            dtype = data_type[key] if key in data_type else np.float
-            minibatch[key] = np.asarray(minibatch[key], dtype=dtype)
-
-        last_values = self.model.step_with_dict(**transitions)['values']
-
-        # Calculate returns and advantages.
-        minibatch['advs'], minibatch['returns'] = \
-            self.advantage_and_returns(values=minibatch['values'],
-                                       rewards=minibatch['rewards'],
-                                       dones=minibatch['dones'],
-                                       last_values=last_values,
-                                       last_dones=self.dones,
-                                       gamma=self.gamma)
-
-        for key in minibatch:
-            minibatch[key] = sf01(minibatch[key])
-
-        minibatch['epinfos'] = epinfos
-        return minibatch
-
-    def advantage_and_returns(self, values, rewards, dones, last_values, last_dones, gamma,
-                              use_non_episodic_rewards=False):
-        """
-        calculate Generalized Advantage Estimation (GAE), https://arxiv.org/abs/1506.02438
-        see also Proximal Policy Optimization Algorithms, https://arxiv.org/abs/1707.06347
-        """
-
-        advantages = np.zeros_like(rewards)
-        lastgaelam = 0  # Lambda used in General Advantage Estimation
+        # discount/bootstrap off value fn
+        mb_returns = np.zeros_like(mb_rewards)
+        mb_advs = np.zeros_like(mb_rewards)
+        lastgaelam = 0
         for t in reversed(range(self.nsteps)):
-            if not use_non_episodic_rewards:
-                if t == self.nsteps - 1:
-                    next_non_terminal = 1.0 - last_dones
-                else:
-                    next_non_terminal = 1.0 - dones[t + 1]
+            if t == self.nsteps - 1:
+                nextnonterminal = 1.0 - self.dones
+                nextvalues = last_values
             else:
-                next_non_terminal = 1.0
-            next_value = values[t + 1] if t < self.nsteps - 1 else last_values
-            delta = rewards[t] + gamma * next_value * next_non_terminal - values[t]
-            advantages[t] = lastgaelam = delta + gamma * self.lam * next_non_terminal * lastgaelam
-        returns = advantages + values
-        return advantages, returns
-
-
+                nextnonterminal = 1.0 - mb_dones[t+1]
+                nextvalues = mb_values[t+1]
+            delta = mb_rewards[t] + self.gamma * nextvalues * nextnonterminal - mb_values[t]
+            mb_advs[t] = lastgaelam = delta + self.gamma * self.lam * nextnonterminal * lastgaelam
+        mb_returns = mb_advs + mb_values
+        return (*map(sf01, (mb_obs, mb_returns, mb_dones, mb_actions, mb_values, mb_neglogpacs)),
+            mb_states, epinfos)
+# obs, returns, masks, actions, values, neglogpacs, states = runner.run()
 def sf01(arr):
     """
     swap and then flatten axes 0 and 1
     """
     s = arr.shape
     return arr.swapaxes(0, 1).reshape(s[0] * s[1], *s[2:])
+
+

baselines/ppo2/test_microbatches.py

@@ -25,11 +25,10 @@ def test_microbatches():
     env_test = DummyVecEnv([env_fn])
     sess_test = make_session(make_default=True, graph=tf.Graph())
     learn_fn(env=env_test, model_fn=partial(MicrobatchedModel, microbatch_size=2))
-    # learn_fn(env=env_test)
     vars_test = {v.name: sess_test.run(v) for v in tf.trainable_variables()}
 
     for v in vars_ref:
-        np.testing.assert_allclose(vars_ref[v], vars_test[v], atol=3e-3)
+        np.testing.assert_allclose(vars_ref[v], vars_test[v], atol=1e-3)
 
 if __name__ == '__main__':
     test_microbatches()

baselines/run.py

@@ -1,5 +1,4 @@
 import sys
-import re
 import multiprocessing
 import os.path as osp
 import gym
@@ -7,13 +6,15 @@ from collections import defaultdict
 import tensorflow as tf
 import numpy as np
 
-from baselines.common.vec_env import VecFrameStack, VecNormalize, VecEnv
 from baselines.common.vec_env.vec_video_recorder import VecVideoRecorder
+from baselines.common.vec_env.vec_frame_stack import VecFrameStack
 from baselines.common.cmd_util import common_arg_parser, parse_unknown_args, make_vec_env, make_env
 from baselines.common.tf_util import get_session
 from baselines import logger
 from importlib import import_module
 
+from baselines.common.vec_env.vec_normalize import VecNormalize
+
 try:
     from mpi4py import MPI
 except ImportError:
@@ -51,7 +52,7 @@ _game_envs['retro'] = {
 
 
 def train(args, extra_args):
-    env_type, env_id = get_env_type(args)
+    env_type, env_id = get_env_type(args.env)
     print('env_type: {}'.format(env_type))
 
     total_timesteps = int(args.num_timesteps)
@@ -63,7 +64,7 @@ def train(args, extra_args):
 
     env = build_env(args)
     if args.save_video_interval != 0:
-        env = VecVideoRecorder(env, osp.join(logger.get_dir(), "videos"), record_video_trigger=lambda x: x % args.save_video_interval == 0, video_length=args.save_video_length)
+        env = VecVideoRecorder(env, osp.join(logger.Logger.CURRENT.dir, "videos"), record_video_trigger=lambda x: x % args.save_video_interval == 0, video_length=args.save_video_length)
 
     if args.network:
         alg_kwargs['network'] = args.network
@@ -90,7 +91,7 @@ def build_env(args):
     alg = args.alg
     seed = args.seed
 
-    env_type, env_id = get_env_type(args)
+    env_type, env_id = get_env_type(args.env)
 
     if env_type in {'atari', 'retro'}:
         if alg == 'deepq':
@@ -103,32 +104,21 @@ def build_env(args):
             env = VecFrameStack(env, frame_stack_size)
 
     else:
-        config = tf.ConfigProto(allow_soft_placement=True,
+       config = tf.ConfigProto(allow_soft_placement=True,
                                intra_op_parallelism_threads=1,
                                inter_op_parallelism_threads=1)
-        config.gpu_options.allow_growth = True
-        get_session(config=config)
+       config.gpu_options.allow_growth = True
+       get_session(config=config)
 
-        flatten_dict_observations = alg not in {'her'}
-        env = make_vec_env(env_id, env_type, args.num_env or 1, seed, reward_scale=args.reward_scale, flatten_dict_observations=flatten_dict_observations)
+       env = make_vec_env(env_id, env_type, args.num_env or 1, seed, reward_scale=args.reward_scale)
 
-        if env_type == 'mujoco':
-            env = VecNormalize(env)
+       if env_type == 'mujoco':
+           env = VecNormalize(env)
 
     return env
 
 
-def get_env_type(args):
-    env_id = args.env
-
-    if args.env_type is not None:
-        return args.env_type, env_id
-
-    # Re-parse the gym registry, since we could have new envs since last time.
-    for env in gym.envs.registry.all():
-        env_type = env._entry_point.split(':')[0].split('.')[-1]
-        _game_envs[env_type].add(env.id)  # This is a set so add is idempotent
-
+def get_env_type(env_id):
     if env_id in _game_envs.keys():
         env_type = env_id
         env_id = [g for g in _game_envs[env_type]][0]
@@ -138,8 +128,6 @@ def get_env_type(args):
             if env_id in e:
                 env_type = g
                 break
-        if ':' in env_id:
-            env_type = re.sub(r':.*', '', env_id)
         assert env_type is not None, 'env_id {} is not recognized in env types'.format(env_id, _game_envs.keys())
 
     return env_type, env_id
@@ -208,6 +196,7 @@ def main(args):
         rank = MPI.COMM_WORLD.Get_rank()
 
     model, env = train(args, extra_args)
+    env.close()
 
     if args.save_path is not None and rank == 0:
         save_path = osp.expanduser(args.save_path)
@@ -215,28 +204,21 @@ def main(args):
 
     if args.play:
         logger.log("Running trained model")
+        env = build_env(args)
         obs = env.reset()
-
-        state = model.initial_state if hasattr(model, 'initial_state') else None
-        dones = np.zeros((1,))
-
-        episode_rew = 0
+        def initialize_placeholders(nlstm=128,**kwargs):
+            return np.zeros((args.num_env or 1, 2*nlstm)), np.zeros((1))
+        state, dones = initialize_placeholders(**extra_args)
         while True:
-            if state is not None:
-                actions, _, state, _ = model.step(obs,S=state, M=dones)
-            else:
-                actions, _, _, _ = model.step(obs)
-
-            obs, rew, done, _ = env.step(actions)
-            episode_rew += rew[0] if isinstance(env, VecEnv) else rew
+            actions, _, state, _ = model.step(obs,S=state, M=dones)
+            obs, _, done, _ = env.step(actions)
             env.render()
             done = done.any() if isinstance(done, np.ndarray) else done
+
             if done:
-                print('episode_rew={}'.format(episode_rew))
-                episode_rew = 0
                 obs = env.reset()
 
-    env.close()
+        env.close()
 
     return model
 

benchmarks_atari10M.htm

@@ -120,7 +120,7 @@
             
             <td>114.26</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         
@@ -152,7 +152,7 @@
             
             <td>131.46</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         
@@ -184,7 +184,7 @@
             
             <td>113.58</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         
@@ -216,7 +216,7 @@
             
             <td>82.94</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         
@@ -248,7 +248,7 @@
             
             <td>81.61</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         
@@ -280,7 +280,7 @@
             
             <td>59.72</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         
@@ -312,7 +312,7 @@
             
             <td>14.98</td>
             
-            <td><a href=https://github.com/openai/baselines/commit/7bfbcf177eca8f46c0c0bfbb378e044539f5e061>7bfbcf1</a></td>
+            <td>cbd21ef</td>
             
         </tr>
         

setup.cfg

@@ -3,5 +3,6 @@ select = F,E999,W291,W293
 exclude = 
     .git,
     __pycache__,
+    baselines/her,
     baselines/ppo1,
     baselines/bench,

setup.py

@@ -53,11 +53,11 @@ setup(name='baselines',
 # ensure there is some tensorflow build with version above 1.4
 import pkg_resources
 tf_pkg = None
-for tf_pkg_name in ['tensorflow', 'tensorflow-gpu', 'tf-nightly', 'tf-nightly-gpu']:
+for tf_pkg_name in ['tensorflow', 'tensorflow-gpu']:
     try:
         tf_pkg = pkg_resources.get_distribution(tf_pkg_name)
     except pkg_resources.DistributionNotFound:
         pass
 assert tf_pkg is not None, 'TensorFlow needed, of version above 1.4'
-from distutils.version import LooseVersion
-assert LooseVersion(re.sub(r'-?rc\d+$', '', tf_pkg.version)) >= LooseVersion('1.4.0')
+from distutils.version import StrictVersion
+assert StrictVersion(re.sub(r'-?rc\d+$', '', tf_pkg.version)) >= StrictVersion('1.4.0')