Monitor should close what it inherits (#1076)

* update to use latest version of gym

* fix imports

* narrow down gym version to 0.15.4 <= gym < 0.16.0

Dockerfile

@@ -11,7 +11,7 @@ WORKDIR $CODE_DIR/baselines
 # Clean up pycache and pyc files
 RUN rm -rf __pycache__ && \
     find . -name "*.pyc" -delete && \
-    pip install tensorflow && \
+    pip install 'tensorflow < 2' && \
     pip install -e .[test]
 
 

README.md

@@ -1,4 +1,4 @@
-**Status:** Active (under active development, breaking changes may occur)
+**Status:** Maintenance (expect bug fixes and minor updates)
 
 <img src="data/logo.jpg" width=25% align="right" /> [![Build status](https://travis-ci.org/openai/baselines.svg?branch=master)](https://travis-ci.org/openai/baselines)
 
@@ -40,7 +40,7 @@ More thorough tutorial on virtualenvs and options can be found [here](https://vi
 
 
 ## Tensorflow versions
-The master branch supports Tensorflow from version 1.4 to 1.14. For Tensorflow 2.0 support, please use tf-2 branch.
+The master branch supports Tensorflow from version 1.4 to 1.14. For Tensorflow 2.0 support, please use tf2 branch.
 
 ## Installation
 - Clone the repo and cd into it:
@@ -48,15 +48,15 @@ The master branch supports Tensorflow from version 1.4 to 1.14. For Tensorflow 2
     git clone https://github.com/openai/baselines.git
     cd baselines
     ```
-- If you don't have TensorFlow installed already, install your favourite flavor of TensorFlow. In most cases, 
+- If you don't have TensorFlow installed already, install your favourite flavor of TensorFlow. In most cases, you may use
     ```bash 
-    pip install tensorflow-gpu # if you have a CUDA-compatible gpu and proper drivers
+    pip install tensorflow-gpu==1.14 # if you have a CUDA-compatible gpu and proper drivers
     ```
     or 
     ```bash
-    pip install tensorflow
+    pip install tensorflow==1.14
     ```
-    should be sufficient. Refer to [TensorFlow installation guide](https://www.tensorflow.org/install/)
+    to install Tensorflow 1.14, which is the latest version of Tensorflow supported by the master branch. Refer to [TensorFlow installation guide](https://www.tensorflow.org/install/)
     for more details. 
 
 - Install baselines package

baselines/acer/acer.py

@@ -6,7 +6,7 @@ from baselines import logger
 
 from baselines.common import set_global_seeds
 from baselines.common.policies import build_policy
-from baselines.common.tf_util import get_session, save_variables
+from baselines.common.tf_util import get_session, save_variables, load_variables
 from baselines.common.vec_env.vec_frame_stack import VecFrameStack
 
 from baselines.a2c.utils import batch_to_seq, seq_to_batch
@@ -216,7 +216,8 @@ class Model(object):
 
 
         self.train = train
-        self.save = functools.partial(save_variables, sess=sess, variables=params)
+        self.save = functools.partial(save_variables, sess=sess)
+        self.load = functools.partial(load_variables, sess=sess)
         self.train_model = train_model
         self.step_model = step_model
         self._step = _step
@@ -358,6 +359,9 @@ def learn(network, env, seed=None, nsteps=20, total_timesteps=int(80e6), q_coef=
                   total_timesteps=total_timesteps, lrschedule=lrschedule, c=c,
                   trust_region=trust_region, alpha=alpha, delta=delta)
 
+    if load_path is not None:
+        model.load(load_path)
+
     runner = Runner(env=env, model=model, nsteps=nsteps)
     if replay_ratio > 0:
         buffer = Buffer(env=env, nsteps=nsteps, size=buffer_size)

baselines/bench/monitor.py

@@ -77,6 +77,7 @@ class Monitor(Wrapper):
         self.total_steps += 1
 
     def close(self):
+        super(Monitor, self).close()
         if self.f is not None:
             self.f.close()
 

baselines/common/cmd_util.py

@@ -9,7 +9,7 @@ except ImportError:
     MPI = None
 
 import gym
-from gym.wrappers import FlattenDictWrapper
+from gym.wrappers import FlattenObservation, FilterObservation
 from baselines import logger
 from baselines.bench import Monitor
 from baselines.common import set_global_seeds
@@ -81,8 +81,7 @@ def make_env(env_id, env_type, mpi_rank=0, subrank=0, seed=None, reward_scale=1.
         env = gym.make(env_id, **env_kwargs)
 
     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 = FlattenObservation(env)
 
     env.seed(seed + subrank if seed is not None else None)
     env = Monitor(env,
@@ -128,7 +127,7 @@ def make_robotics_env(env_id, seed, rank=0):
     """
     set_global_seeds(seed)
     env = gym.make(env_id)
-    env = FlattenDictWrapper(env, ['observation', 'desired_goal'])
+    env = FlattenObservation(FilterObservation(env, ['observation', 'desired_goal']))
     env = Monitor(
         env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)),
         info_keywords=('is_success',))

baselines/common/mpi_moments.py

@@ -12,8 +12,9 @@ def mpi_mean(x, axis=0, comm=None, keepdims=False):
     localsum = np.zeros(n+1, x.dtype)
     localsum[:n] = xsum.ravel()
     localsum[n] = x.shape[axis]
-    globalsum = np.zeros_like(localsum)
-    comm.Allreduce(localsum, globalsum, op=MPI.SUM)
+    # globalsum = np.zeros_like(localsum)
+    # comm.Allreduce(localsum, globalsum, op=MPI.SUM)
+    globalsum = comm.allreduce(localsum, op=MPI.SUM)
     return globalsum[:n].reshape(xsum.shape) / globalsum[n], globalsum[n]
 
 def mpi_moments(x, axis=0, comm=None, keepdims=False):

baselines/common/vec_env/subproc_vec_env.py

@@ -26,7 +26,7 @@ def worker(remote, parent_remote, env_fn_wrappers):
                 remote.close()
                 break
             elif cmd == 'get_spaces_spec':
-                remote.send((envs[0].observation_space, envs[0].action_space, envs[0].spec))
+                remote.send(CloudpickleWrapper((envs[0].observation_space, envs[0].action_space, envs[0].spec)))
             else:
                 raise NotImplementedError
     except KeyboardInterrupt:
@@ -68,7 +68,7 @@ class SubprocVecEnv(VecEnv):
             remote.close()
 
         self.remotes[0].send(('get_spaces_spec', None))
-        observation_space, action_space, self.spec = self.remotes[0].recv()
+        observation_space, action_space, self.spec = self.remotes[0].recv().x
         self.viewer = None
         VecEnv.__init__(self, nenvs, observation_space, action_space)
 

baselines/gail/behavior_clone.py

@@ -23,7 +23,7 @@ from baselines.gail.dataset.mujoco_dset import Mujoco_Dset
 
 def argsparser():
     parser = argparse.ArgumentParser("Tensorflow Implementation of Behavior Cloning")
-    parser.add_argument('--env_id', help='environment ID', default='Hopper-v1')
+    parser.add_argument('--env_id', help='environment ID', default='Hopper-v2')
     parser.add_argument('--seed', help='RNG seed', type=int, default=0)
     parser.add_argument('--expert_path', type=str, default='data/deterministic.trpo.Hopper.0.00.npz')
     parser.add_argument('--checkpoint_dir', help='the directory to save model', default='checkpoint')
@@ -73,7 +73,7 @@ def learn(env, policy_func, dataset, optim_batch_size=128, max_iters=1e4,
         savedir_fname = tempfile.TemporaryDirectory().name
     else:
         savedir_fname = osp.join(ckpt_dir, task_name)
-    U.save_state(savedir_fname, var_list=pi.get_variables())
+    U.save_variables(savedir_fname, variables=pi.get_variables())
     return savedir_fname
 
 

baselines/gail/run_mujoco.py

@@ -165,7 +165,7 @@ def runner(env, policy_func, load_model_path, timesteps_per_batch, number_trajs,
     U.initialize()
     # Prepare for rollouts
     # ----------------------------------------
-    U.load_state(load_model_path)
+    U.load_variables(load_model_path)
 
     obs_list = []
     acs_list = []

baselines/run.py

@@ -226,7 +226,7 @@ def main(args):
         state = model.initial_state if hasattr(model, 'initial_state') else None
         dones = np.zeros((1,))
 
-        episode_rew = 0
+        episode_rew = np.zeros(env.num_envs) if isinstance(env, VecEnv) else np.zeros(1)
         while True:
             if state is not None:
                 actions, _, state, _ = model.step(obs,S=state, M=dones)
@@ -234,13 +234,13 @@ def main(args):
                 actions, _, _, _ = model.step(obs)
 
             obs, rew, done, _ = env.step(actions)
-            episode_rew += rew[0] if isinstance(env, VecEnv) else rew
+            episode_rew += rew
             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()
+            done_any = done.any() if isinstance(done, np.ndarray) else done
+            if done_any:
+                for i in np.nonzero(done)[0]:
+                    print('episode_rew={}'.format(episode_rew[i]))
+                    episode_rew[i] = 0
 
     env.close()
 

setup.py

@@ -31,7 +31,7 @@ setup(name='baselines',
       packages=[package for package in find_packages()
                 if package.startswith('baselines')],
       install_requires=[
-          'gym>=0.10.0, <1.0.0',
+          'gym>=0.15.4, <0.16.0',
           'scipy',
           'tqdm',
           'joblib',