trpo - increase reward and eplen buffer to 100 for consistency

* joshim5 changes (width and height to WarpFrame wrapper)

* match network output with action distribution via a linear layer only if necessary (#167)

* support color vs. grayscale option in WarpFrame wrapper (#166)

* support color vs. grayscale option in WarpFrame wrapper

* Support color in other wrappers

* Updated per Peters suggestions

* fixing test failures

* ppo2 with microbatches (#168)

* pass microbatch_size to the model during construction

* microbatch fixes and test (#169)

* microbatch fixes and test

* tiny cleanup

* added assertions to the test

* vpg-related fix

* Peterz joshim5 subclass ppo2 model (#170)

* microbatch fixes and test

* tiny cleanup

* added assertions to the test

* vpg-related fix

* subclassing the model to make microbatched version of model WIP

* made microbatched model a subclass of ppo2 Model

* flake8 complaint

* mpi-less ppo2 (resolving merge conflict)

* flake8 and mpi4py imports in ppo2/model.py

* more un-mpying

.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 .

Dockerfile

@@ -1,16 +1,9 @@
-FROM ubuntu:16.04
+FROM python:3.6
+
+RUN apt-get -y update && apt-get -y install ffmpeg
+# RUN apt-get -y update && apt-get -y install git wget python-dev python3-dev libopenmpi-dev python-pip zlib1g-dev cmake python-opencv
 
-RUN apt-get -y update && apt-get -y install git wget python-dev python3-dev libopenmpi-dev python-pip zlib1g-dev cmake python-opencv
 ENV CODE_DIR /root/code
-ENV VENV /root/venv
-
-RUN \
-    pip install virtualenv && \
-    virtualenv $VENV --python=python3 && \
-    . $VENV/bin/activate && \
-    pip install --upgrade pip
-
-ENV PATH=$VENV/bin:$PATH
 
 COPY . $CODE_DIR/baselines
 WORKDIR $CODE_DIR/baselines

README.md

@@ -109,17 +109,9 @@ python -m baselines.run --alg=ppo2 --env=PongNoFrameskip-v4 --num_timesteps=0 --
 
 *NOTE:* At the moment Mujoco training uses VecNormalize wrapper for the environment which is not being saved correctly; so loading the models trained on Mujoco will not work well if the environment is recreated. If necessary, you can work around that by replacing RunningMeanStd by TfRunningMeanStd in [baselines/common/vec_env/vec_normalize.py](baselines/common/vec_env/vec_normalize.py#L12). This way, mean and std of environment normalizing wrapper will be saved in tensorflow variables and included in the model file; however, training is slower that way - hence not including it by default
 
+## Loading and vizualizing learning curves and other training metrics
+See [here](docs/viz/viz.ipynb) for instructions on how to load and display the training data. 
 
-## Using baselines with TensorBoard
-Baselines logger can save data in the TensorBoard format. To do so, set environment variables `OPENAI_LOG_FORMAT` and `OPENAI_LOGDIR`:
-```bash
-export OPENAI_LOG_FORMAT='stdout,log,csv,tensorboard' # formats are comma-separated, but for tensorboard you only really need the last one
-export OPENAI_LOGDIR=path/to/tensorboard/data
-```
-And you can now start TensorBoard with:
-```bash
-tensorboard --logdir=$OPENAI_LOGDIR
-```
 ## Subpackages
 
 - [A2C](baselines/a2c)

baselines/common/atari_wrappers.py

@@ -129,18 +129,26 @@ class ClipRewardEnv(gym.RewardWrapper):
         return np.sign(reward)
 
 class WarpFrame(gym.ObservationWrapper):
-    def __init__(self, env):
+    def __init__(self, env, width=84, height=84, grayscale=True):
         """Warp frames to 84x84 as done in the Nature paper and later work."""
         gym.ObservationWrapper.__init__(self, env)
-        self.width = 84
+        self.width = width
-        self.height = 84
+        self.height = height
-        self.observation_space = spaces.Box(low=0, high=255,
+        self.grayscale = grayscale
-            shape=(self.height, self.width, 1), dtype=np.uint8)
+        if self.grayscale:
+            self.observation_space = spaces.Box(low=0, high=255,
+                shape=(self.height, self.width, 1), dtype=np.uint8)
+        else:
+            self.observation_space = spaces.Box(low=0, high=255,
+                shape=(self.height, self.width, 3), dtype=np.uint8)
 
     def observation(self, frame):
-        frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        if self.grayscale:
+            frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
         frame = cv2.resize(frame, (self.width, self.height), interpolation=cv2.INTER_AREA)
-        return frame[:, :, None]
+        if self.grayscale:
+            frame = np.expand_dims(frame, -1)
+        return frame
 
 class FrameStack(gym.Wrapper):
     def __init__(self, env, k):
@@ -156,7 +164,7 @@ class FrameStack(gym.Wrapper):
         self.k = k
         self.frames = deque([], maxlen=k)
         shp = env.observation_space.shape
-        self.observation_space = spaces.Box(low=0, high=255, shape=(shp[0], shp[1], shp[2] * k), dtype=env.observation_space.dtype)
+        self.observation_space = spaces.Box(low=0, high=255, shape=(shp[:-1] + (shp[-1] * k,)), dtype=env.observation_space.dtype)
 
     def reset(self):
         ob = self.env.reset()
@@ -197,7 +205,7 @@ class LazyFrames(object):
 
     def _force(self):
         if self._out is None:
-            self._out = np.concatenate(self._frames, axis=2)
+            self._out = np.concatenate(self._frames, axis=-1)
             self._frames = None
         return self._out
 

baselines/common/cmd_util.py

@@ -60,12 +60,14 @@ def make_env(env_id, env_type, subrank=0, seed=None, reward_scale=1.0, gamestate
                   allow_early_resets=True)
 
     if env_type == 'atari':
-         return wrap_deepmind(env, **wrapper_kwargs)
+        env = wrap_deepmind(env, **wrapper_kwargs)
-    elif reward_scale != 1:
+    elif env_type == 'retro':
-         return retro_wrappers.RewardScaler(env, reward_scale)
+        env = retro_wrappers.wrap_deepmind_retro(env, **wrapper_kwargs)
-    else:
-        return env
 
+    if reward_scale != 1:
+        env = retro_wrappers.RewardScaler(env, reward_scale)
+
+    return env
 
 
 def make_mujoco_env(env_id, seed, reward_scale=1.0):
@@ -129,6 +131,8 @@ def common_arg_parser():
     parser.add_argument('--num_env', help='Number of environment copies being run in parallel. When not specified, set to number of cpus for Atari, and to 1 for Mujoco', default=None, type=int)
     parser.add_argument('--reward_scale', help='Reward scale factor. Default: 1.0', default=1.0, type=float)
     parser.add_argument('--save_path', help='Path to save trained model to', default=None, type=str)
+    parser.add_argument('--save_video_interval', help='Save video every x steps (0 = disabled)', default=0, type=int)
+    parser.add_argument('--save_video_length', help='Length of recorded video. Default: 200', default=200, type=int)
     parser.add_argument('--play', default=False, action='store_true')
     return parser
 

baselines/common/distributions.py

@@ -62,7 +62,7 @@ class CategoricalPdType(PdType):
     def pdclass(self):
         return CategoricalPd
     def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
-        pdparam = fc(latent_vector, 'pi', self.ncat, init_scale=init_scale, init_bias=init_bias)
+        pdparam = _matching_fc(latent_vector, 'pi', self.ncat, init_scale=init_scale, init_bias=init_bias)
         return self.pdfromflat(pdparam), pdparam
 
     def param_shape(self):
@@ -82,7 +82,7 @@ class MultiCategoricalPdType(PdType):
         return MultiCategoricalPd(self.ncats, flat)
 
     def pdfromlatent(self, latent, init_scale=1.0, init_bias=0.0):
-        pdparam = fc(latent, 'pi', self.ncats.sum(), init_scale=init_scale, init_bias=init_bias)
+        pdparam = _matching_fc(latent, 'pi', self.ncats.sum(), init_scale=init_scale, init_bias=init_bias)
         return self.pdfromflat(pdparam), pdparam
 
     def param_shape(self):
@@ -99,7 +99,7 @@ class DiagGaussianPdType(PdType):
         return DiagGaussianPd
 
     def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
-        mean = fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
+        mean = _matching_fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
         logstd = tf.get_variable(name='pi/logstd', shape=[1, self.size], initializer=tf.zeros_initializer())
         pdparam = tf.concat([mean, mean * 0.0 + logstd], axis=1)
         return self.pdfromflat(pdparam), mean
@@ -123,7 +123,7 @@ class BernoulliPdType(PdType):
     def sample_dtype(self):
         return tf.int32
     def pdfromlatent(self, latent_vector, init_scale=1.0, init_bias=0.0):
-        pdparam = fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
+        pdparam = _matching_fc(latent_vector, 'pi', self.size, init_scale=init_scale, init_bias=init_bias)
         return self.pdfromflat(pdparam), pdparam
 
 # WRONG SECOND DERIVATIVES
@@ -345,3 +345,9 @@ def validate_probtype(probtype, pdparam):
     assert np.abs(klval - klval_ll) < 3 * klval_ll_stderr # within 3 sigmas
     print('ok on', probtype, pdparam)
 
+
+def _matching_fc(tensor, name, size, init_scale, init_bias):
+    if tensor.shape[-1] == size:
+        return tensor
+    else:
+        return fc(tensor, name, size, init_scale=init_scale, init_bias=init_bias)

baselines/common/mpi_adam.py

@@ -1,7 +1,11 @@
-from mpi4py import MPI
 import baselines.common.tf_util as U
 import tensorflow as tf
 import numpy as np
+try:
+    from mpi4py import MPI
+except ImportError:
+    MPI = None
+
 
 class MpiAdam(object):
     def __init__(self, var_list, *, beta1=0.9, beta2=0.999, epsilon=1e-08, scale_grad_by_procs=True, comm=None):
@@ -16,16 +20,19 @@ class MpiAdam(object):
         self.t = 0
         self.setfromflat = U.SetFromFlat(var_list)
         self.getflat = U.GetFlat(var_list)
-        self.comm = MPI.COMM_WORLD if comm is None else comm
+        self.comm = MPI.COMM_WORLD if comm is None and MPI is not None else comm
 
     def update(self, localg, stepsize):
         if self.t % 100 == 0:
             self.check_synced()
         localg = localg.astype('float32')
-        globalg = np.zeros_like(localg)
+        if self.comm is not None:
-        self.comm.Allreduce(localg, globalg, op=MPI.SUM)
+            globalg = np.zeros_like(localg)
-        if self.scale_grad_by_procs:
+            self.comm.Allreduce(localg, globalg, op=MPI.SUM)
-            globalg /= self.comm.Get_size()
+            if self.scale_grad_by_procs:
+                globalg /= self.comm.Get_size()
+        else:
+            globalg = np.copy(localg)
 
         self.t += 1
         a = stepsize * np.sqrt(1 - self.beta2**self.t)/(1 - self.beta1**self.t)
@@ -35,11 +42,15 @@ class MpiAdam(object):
         self.setfromflat(self.getflat() + step)
 
     def sync(self):
+        if self.comm is None:
+            return
         theta = self.getflat()
         self.comm.Bcast(theta, root=0)
         self.setfromflat(theta)
 
     def check_synced(self):
+        if self.comm is None:
+            return
         if self.comm.Get_rank() == 0: # this is root
             theta = self.getflat()
             self.comm.Bcast(theta, root=0)
@@ -63,17 +74,30 @@ def test_MpiAdam():
     do_update = U.function([], loss, updates=[update_op])
 
     tf.get_default_session().run(tf.global_variables_initializer())
+    losslist_ref = []
     for i in range(10):
-        print(i,do_update())
+        l = do_update()
+        print(i, l)
+        losslist_ref.append(l)
+
+
 
     tf.set_random_seed(0)
     tf.get_default_session().run(tf.global_variables_initializer())
 
     var_list = [a,b]
-    lossandgrad = U.function([], [loss, U.flatgrad(loss, var_list)], updates=[update_op])
+    lossandgrad = U.function([], [loss, U.flatgrad(loss, var_list)])
     adam = MpiAdam(var_list)
 
+    losslist_test = []
     for i in range(10):
         l,g = lossandgrad()
         adam.update(g, stepsize)
         print(i,l)
+        losslist_test.append(l)
+
+    np.testing.assert_allclose(np.array(losslist_ref), np.array(losslist_test), atol=1e-4)
+
+
+if __name__ == '__main__':
+    test_MpiAdam()

baselines/common/mpi_running_mean_std.py

@@ -1,4 +1,8 @@
-from mpi4py import MPI
+try:
+    from mpi4py import MPI
+except ImportError:
+    MPI = None
+
 import tensorflow as tf, baselines.common.tf_util as U, numpy as np
 
 class RunningMeanStd(object):
@@ -39,7 +43,8 @@ class RunningMeanStd(object):
         n = int(np.prod(self.shape))
         totalvec = np.zeros(n*2+1, 'float64')
         addvec = np.concatenate([x.sum(axis=0).ravel(), np.square(x).sum(axis=0).ravel(), np.array([len(x)],dtype='float64')])
-        MPI.COMM_WORLD.Allreduce(addvec, totalvec, op=MPI.SUM)
+        if MPI is not None:
+            MPI.COMM_WORLD.Allreduce(addvec, totalvec, op=MPI.SUM)
         self.incfiltparams(totalvec[0:n].reshape(self.shape), totalvec[n:2*n].reshape(self.shape), totalvec[2*n])
 
 @U.in_session

baselines/common/plot_util.py

@@ -0,0 +1,401 @@
+import matplotlib.pyplot as plt
+import os.path as osp
+import json
+import os
+import numpy as np
+import pandas
+from collections import defaultdict, namedtuple
+from baselines.bench import monitor
+from baselines.logger import read_json, read_csv
+
+def smooth(y, radius, mode='two_sided', valid_only=False):
+    '''
+    Smooth signal y, where radius is determines the size of the window
+
+    mode='twosided':
+        average over the window [max(index - radius, 0), min(index + radius, len(y)-1)]
+    mode='causal':
+        average over the window [max(index - radius, 0), index]
+
+    valid_only: put nan in entries where the full-sized window is not available
+
+    '''
+    assert mode in ('two_sided', 'causal')
+    if len(y) < 2*radius+1:
+        return np.ones_like(y) * y.mean()
+    elif mode == 'two_sided':
+        convkernel = np.ones(2 * radius+1)
+        out = np.convolve(y, convkernel,mode='same') / np.convolve(np.ones_like(y), convkernel, mode='same')
+        if valid_only:
+            out[:radius] = out[-radius:] = np.nan
+    elif mode == 'causal':
+        convkernel = np.ones(radius)
+        out = np.convolve(y, convkernel,mode='full') / np.convolve(np.ones_like(y), convkernel, mode='full')
+        out = out[:-radius+1]
+        if valid_only:
+            out[:radius] = np.nan
+    return out
+
+def one_sided_ema(xolds, yolds, low=None, high=None, n=512, decay_steps=1., low_counts_threshold=1e-8):
+    '''
+    perform one-sided (causal) EMA (exponential moving average)
+    smoothing and resampling to an even grid with n points.
+    Does not do extrapolation, so we assume
+    xolds[0] <= low && high <= xolds[-1]
+
+    Arguments:
+
+    xolds: array or list  - x values of data. Needs to be sorted in ascending order
+    yolds: array of list  - y values of data. Has to have the same length as xolds
+
+    low: float            - min value of the new x grid. By default equals to xolds[0]
+    high: float           - max value of the new x grid. By default equals to xolds[-1]
+
+    n: int                - number of points in new x grid
+
+    decay_steps: float    - EMA decay factor, expressed in new x grid steps.
+
+    low_counts_threshold: float or int
+                          - y values with counts less than this value will be set to NaN
+
+    Returns:
+        tuple sum_ys, count_ys where
+            xs        - array with new x grid
+            ys        - array of EMA of y at each point of the new x grid
+            count_ys  - array of EMA of y counts at each point of the new x grid
+
+    '''
+
+    low = xolds[0] if low is None else low
+    high = xolds[-1] if high is None else high
+
+    assert xolds[0] <= low, 'low = {} < xolds[0] = {} - extrapolation not permitted!'.format(low, xolds[0])
+    assert xolds[-1] >= high, 'high = {} > xolds[-1] = {}  - extrapolation not permitted!'.format(high, xolds[-1])
+    assert len(xolds) == len(yolds), 'length of xolds ({}) and yolds ({}) do not match!'.format(len(xolds), len(yolds))
+
+
+    xolds = xolds.astype('float64')
+    yolds = yolds.astype('float64')
+
+    luoi = 0 # last unused old index
+    sum_y = 0.
+    count_y = 0.
+    xnews = np.linspace(low, high, n)
+    decay_period = (high - low) / (n - 1) * decay_steps
+    interstep_decay = np.exp(- 1. / decay_steps)
+    sum_ys = np.zeros_like(xnews)
+    count_ys = np.zeros_like(xnews)
+    for i in range(n):
+        xnew = xnews[i]
+        sum_y *= interstep_decay
+        count_y *= interstep_decay
+        while True:
+            xold = xolds[luoi]
+            if xold <= xnew:
+                decay = np.exp(- (xnew - xold) / decay_period)
+                sum_y += decay * yolds[luoi]
+                count_y += decay
+                luoi += 1
+            else:
+                break
+            if luoi >= len(xolds):
+                break
+        sum_ys[i] = sum_y
+        count_ys[i] = count_y
+
+    ys = sum_ys / count_ys
+    ys[count_ys < low_counts_threshold] = np.nan
+
+    return xnews, ys, count_ys
+
+def symmetric_ema(xolds, yolds, low=None, high=None, n=512, decay_steps=1., low_counts_threshold=1e-8):
+    '''
+    perform symmetric EMA (exponential moving average)
+    smoothing and resampling to an even grid with n points.
+    Does not do extrapolation, so we assume
+    xolds[0] <= low && high <= xolds[-1]
+
+    Arguments:
+
+    xolds: array or list  - x values of data. Needs to be sorted in ascending order
+    yolds: array of list  - y values of data. Has to have the same length as xolds
+
+    low: float            - min value of the new x grid. By default equals to xolds[0]
+    high: float           - max value of the new x grid. By default equals to xolds[-1]
+
+    n: int                - number of points in new x grid
+
+    decay_steps: float    - EMA decay factor, expressed in new x grid steps.
+
+    low_counts_threshold: float or int
+                          - y values with counts less than this value will be set to NaN
+
+    Returns:
+        tuple sum_ys, count_ys where
+            xs        - array with new x grid
+            ys        - array of EMA of y at each point of the new x grid
+            count_ys  - array of EMA of y counts at each point of the new x grid
+
+    '''
+    xs, ys1, count_ys1 = one_sided_ema(xolds, yolds, low, high, n, decay_steps, low_counts_threshold=0)
+    _,  ys2, count_ys2 = one_sided_ema(-xolds[::-1], yolds[::-1], -high, -low, n, decay_steps, low_counts_threshold=0)
+    ys2 = ys2[::-1]
+    count_ys2 = count_ys2[::-1]
+    count_ys = count_ys1 + count_ys2
+    ys = (ys1 * count_ys1 + ys2 * count_ys2) / count_ys
+    ys[count_ys < low_counts_threshold] = np.nan
+    return xs, ys, count_ys
+
+Result = namedtuple('Result', 'monitor progress dirname metadata')
+Result.__new__.__defaults__ = (None,) * len(Result._fields)
+
+def load_results(root_dir_or_dirs, enable_progress=True, enable_monitor=True, verbose=False):
+    '''
+    load summaries of runs from a list of directories (including subdirectories)
+    Arguments:
+
+    enable_progress: bool - if True, will attempt to load data from progress.csv files (data saved by logger). Default: True
+
+    enable_monitor: bool - if True, will attempt to load data from monitor.csv files (data saved by Monitor environment wrapper). Default: True
+
+    verbose: bool - if True, will print out list of directories from which the data is loaded. Default: False
+
+
+    Returns:
+    List of Result objects with the following fields:
+         - dirname - path to the directory data was loaded from
+         - metadata - run metadata (such as command-line arguments and anything else in metadata.json file
+         - 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
+    '''
+    if isinstance(root_dir_or_dirs, str):
+        rootdirs = [osp.expanduser(root_dir_or_dirs)]
+    else:
+        rootdirs = [osp.expanduser(d) for d in root_dir_or_dirs]
+    allresults = []
+    for rootdir in rootdirs:
+        assert osp.exists(rootdir), "%s doesn't exist"%rootdir
+        for dirname, dirs, files in os.walk(rootdir):
+            if '-proc' in dirname:
+                files[:] = []
+                continue
+            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[:] = []
+                result = {'dirname' : dirname}
+                if "metadata.json" in files:
+                    with open(osp.join(dirname, "metadata.json"), "r") as fh:
+                        result['metadata'] = json.load(fh)
+                progjson = osp.join(dirname, "progress.json")
+                progcsv = osp.join(dirname, "progress.csv")
+                if enable_progress:
+                    if osp.exists(progjson):
+                        result['progress'] = pandas.DataFrame(read_json(progjson))
+                    elif osp.exists(progcsv):
+                        try:
+                            result['progress'] = read_csv(progcsv)
+                        except pandas.errors.EmptyDataError:
+                            print('skipping progress file in ', dirname, 'empty data')
+                    else:
+                        if verbose: print('skipping %s: no progress file'%dirname)
+
+                if enable_monitor:
+                    try:
+                        result['monitor'] = pandas.DataFrame(monitor.load_results(dirname))
+                    except monitor.LoadMonitorResultsError:
+                        print('skipping %s: no monitor files'%dirname)
+                    except Exception as e:
+                        print('exception loading monitor file in %s: %s'%(dirname, e))
+
+                if result.get('monitor') is not None or result.get('progress') is not None:
+                    allresults.append(Result(**result))
+                    if verbose:
+                        print('successfully loaded %s'%dirname)
+
+    if verbose: print('loaded %i results'%len(allresults))
+    return allresults
+
+COLORS = ['blue', 'green', 'red', 'cyan', 'magenta', 'yellow', 'black', 'purple', 'pink',
+        'brown', 'orange', 'teal',  'lightblue', 'lime', 'lavender', 'turquoise',
+        'darkgreen', 'tan', 'salmon', 'gold',  'darkred', 'darkblue']
+
+
+def default_xy_fn(r):
+    x = np.cumsum(r.monitor.l)
+    y = smooth(r.monitor.r, radius=10)
+    return x,y
+
+def default_split_fn(r):
+    import re
+    # match name between slash and -<digits> at the end of the string
+    # (slash in the beginning or -<digits> in the end or either may be missing)
+    match = re.search(r'[^/-]+(?=(-\d+)?\Z)', r.dirname)
+    if match:
+        return match.group(0)
+
+def plot_results(
+    allresults, *,
+    xy_fn=default_xy_fn,
+    split_fn=default_split_fn,
+    group_fn=default_split_fn,
+    average_group=False,
+    shaded_std=True,
+    shaded_err=True,
+    figsize=None,
+    legend_outside=False,
+    resample=0,
+    smooth_step=1.0,
+):
+    '''
+    Plot multiple Results objects
+
+    xy_fn: function Result -> x,y           - function that converts results objects into tuple of x and y values.
+                                              By default, x is cumsum of episode lengths, and y is episode rewards
+
+    split_fn: function Result -> hashable   - function that converts results objects into keys to split curves into sub-panels by.
+                                              That is, the results r for which split_fn(r) is different will be put on different sub-panels.
+                                              By default, the portion of r.dirname between last / and -<digits> is returned. The sub-panels are
+                                              stacked vertically in the figure.
+
+    group_fn: function Result -> hashable   - function that converts results objects into keys to group curves by.
+                                              That is, the results r for which group_fn(r) is the same will be put into the same group.
+                                              Curves in the same group have the same color (if average_group is False), or averaged over
+                                              (if average_group is True). The default value is the same as default value for split_fn
+
+    average_group: bool                     - if True, will average the curves in the same group and plot the mean. Enables resampling
+                                              (if resample = 0, will use 512 steps)
+
+    shaded_std: bool                        - if True (default), the shaded region corresponding to standard deviation of the group of curves will be
+                                              shown (only applicable if average_group = True)
+
+    shaded_err: bool                        - if True (default), the shaded region corresponding to error in mean estimate of the group of curves
+                                              (that is, standard deviation divided by square root of number of curves) will be
+                                              shown (only applicable if average_group = True)
+
+    figsize: tuple or None                  - size of the resulting figure (including sub-panels). By default, width is 6 and height is 6 times number of
+                                              sub-panels.
+
+
+    legend_outside: bool                    - if True, will place the legend outside of the sub-panels.
+
+    resample: int                           - if not zero, size of the uniform grid in x direction to resample onto. Resampling is performed via symmetric
+                                              EMA smoothing (see the docstring for symmetric_ema).
+                                              Default is zero (no resampling). Note that if average_group is True, resampling is necessary; in that case, default
+                                              value is 512.
+
+    smooth_step: float                      - when resampling (i.e. when resample > 0 or average_group is True), use this EMA decay parameter (in units of the new grid step).
+                                              See docstrings for decay_steps in symmetric_ema or one_sided_ema functions.
+
+    '''
+
+    if split_fn is None: split_fn = lambda _ : ''
+    if group_fn is None: group_fn = lambda _ : ''
+    sk2r = defaultdict(list) # splitkey2results
+    for result in allresults:
+        splitkey = split_fn(result)
+        sk2r[splitkey].append(result)
+    assert len(sk2r) > 0
+    assert isinstance(resample, int), "0: don't resample. <integer>: that many samples"
+    nrows = len(sk2r)
+    ncols = 1
+    figsize = figsize or (6, 6 * nrows)
+    f, axarr = plt.subplots(nrows, ncols, sharex=False, squeeze=False, figsize=figsize)
+
+    groups = list(set(group_fn(result) for result in allresults))
+
+    default_samples = 512
+    if average_group:
+        resample = resample or default_samples
+
+    for (isplit, sk) in enumerate(sorted(sk2r.keys())):
+        g2l = {}
+        g2c = defaultdict(int)
+        sresults = sk2r[sk]
+        gresults = defaultdict(list)
+        ax = axarr[isplit][0]
+        for result in sresults:
+            group = group_fn(result)
+            g2c[group] += 1
+            x, y = xy_fn(result)
+            if x is None: x = np.arange(len(y))
+            x, y = map(np.asarray, (x, y))
+            if average_group:
+                gresults[group].append((x,y))
+            else:
+                if resample:
+                    x, y, counts = symmetric_ema(x, y, x[0], x[-1], resample, decay_steps=smooth_step)
+                l, = ax.plot(x, y, color=COLORS[groups.index(group) % len(COLORS)])
+                g2l[group] = l
+        if average_group:
+            for group in sorted(groups):
+                xys = gresults[group]
+                if not any(xys):
+                    continue
+                color = COLORS[groups.index(group) % len(COLORS)]
+                origxs = [xy[0] for xy in xys]
+                minxlen = min(map(len, origxs))
+                def allequal(qs):
+                    return all((q==qs[0]).all() for q in qs[1:])
+                if resample:
+                    low  = max(x[0] for x in origxs)
+                    high = min(x[-1] for x in origxs)
+                    usex = np.linspace(low, high, resample)
+                    ys = []
+                    for (x, y) in xys:
+                        ys.append(symmetric_ema(x, y, low, high, resample, decay_steps=smooth_step)[1])
+                else:
+                    assert allequal([x[:minxlen] for x in origxs]),\
+                        'If you want to average unevenly sampled data, set resample=<number of samples you want>'
+                    usex = origxs[0]
+                    ys = [xy[1][:minxlen] for xy in xys]
+                ymean = np.mean(ys, axis=0)
+                ystd = np.std(ys, axis=0)
+                ystderr = ystd / np.sqrt(len(ys))
+                l, = axarr[isplit][0].plot(usex, ymean, color=color)
+                g2l[group] = l
+                if shaded_err:
+                    ax.fill_between(usex, ymean - ystderr, ymean + ystderr, color=color, alpha=.4)
+                if shaded_std:
+                    ax.fill_between(usex, ymean - ystd,    ymean + ystd,    color=color, alpha=.2)
+
+
+        # https://matplotlib.org/users/legend_guide.html
+        plt.tight_layout()
+        if any(g2l.keys()):
+            ax.legend(
+                g2l.values(),
+                ['%s (%i)'%(g, g2c[g]) for g in g2l] if average_group else g2l.keys(),
+                loc=2 if legend_outside else None,
+                bbox_to_anchor=(1,1) if legend_outside else None)
+        ax.set_title(sk)
+    return f, axarr
+
+def regression_analysis(df):
+    xcols = list(df.columns.copy())
+    xcols.remove('score')
+    ycols = ['score']
+    import statsmodels.api as sm
+    mod = sm.OLS(df[ycols], sm.add_constant(df[xcols]), hasconst=False)
+    res = mod.fit()
+    print(res.summary())
+
+def test_smooth():
+    norig = 100
+    nup = 300
+    ndown = 30
+    xs = np.cumsum(np.random.rand(norig) * 10 / norig)
+    yclean = np.sin(xs)
+    ys = yclean + .1 * np.random.randn(yclean.size)
+    xup, yup, _ = symmetric_ema(xs, ys, xs.min(), xs.max(), nup, decay_steps=nup/ndown)
+    xdown, ydown, _ = symmetric_ema(xs, ys, xs.min(), xs.max(), ndown, decay_steps=ndown/ndown)
+    xsame, ysame, _ = symmetric_ema(xs, ys, xs.min(), xs.max(), norig, decay_steps=norig/ndown)
+    plt.plot(xs, ys, label='orig', marker='x')
+    plt.plot(xup, yup, label='up', marker='x')
+    plt.plot(xdown, ydown, label='down', marker='x')
+    plt.plot(xsame, ysame, label='same', marker='x')
+    plt.plot(xs, yclean, label='clean', marker='x')
+    plt.legend()
+    plt.show()
+
+

baselines/common/retro_wrappers.py

@@ -132,10 +132,8 @@ class MovieRecord(gym.Wrapper):
         self.epcount = 0
     def reset(self):
         if self.epcount % self.k == 0:
-            print('saving movie this episode', self.savedir)
             self.env.unwrapped.movie_path = self.savedir
         else:
-            print('not saving this episode')
             self.env.unwrapped.movie_path = None
             self.env.unwrapped.movie = None
         self.epcount += 1

baselines/common/tests/test_serialization.py

@@ -103,9 +103,9 @@ def test_coexistence(learn_fn, network_fn):
     kwargs.update(learn_kwargs[learn_fn])
 
     learn =  partial(learn, env=env, network=network_fn, total_timesteps=0, **kwargs)
-    make_session(make_default=True, graph=tf.Graph());
+    make_session(make_default=True, graph=tf.Graph())
     model1 = learn(seed=1)
-    make_session(make_default=True, graph=tf.Graph());
+    make_session(make_default=True, graph=tf.Graph())
     model2 = learn(seed=2)
 
     model1.step(env.observation_space.sample())

baselines/common/vec_env/__init__.py

@@ -32,6 +32,11 @@ class VecEnv(ABC):
     """
     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

baselines/common/vec_env/dummy_vec_env.py

@@ -20,9 +20,6 @@ class DummyVecEnv(VecEnv):
         env = self.envs[0]
         VecEnv.__init__(self, len(env_fns), env.observation_space, env.action_space)
         obs_space = env.observation_space
-        if isinstance(obs_space, spaces.MultiDiscrete):
-            obs_space.shape = obs_space.shape[0]
-
         self.keys, shapes, dtypes = obs_space_info(obs_space)
 
         self.buf_obs = { k: np.zeros((self.num_envs,) + tuple(shapes[k]), dtype=dtypes[k]) for k in self.keys }
@@ -79,6 +76,6 @@ class DummyVecEnv(VecEnv):
 
     def render(self, mode='human'):
         if self.num_envs == 1:
-            self.envs[0].render(mode=mode)
+            return self.envs[0].render(mode=mode)
         else:
-            super().render(mode=mode)
+            return super().render(mode=mode)

baselines/common/vec_env/test_video_recorder.py

@@ -0,0 +1,49 @@
+"""
+Tests for asynchronous vectorized environments.
+"""
+
+import gym
+import pytest
+import os
+import glob
+import tempfile
+
+from .dummy_vec_env import DummyVecEnv
+from .shmem_vec_env import ShmemVecEnv
+from .subproc_vec_env import SubprocVecEnv
+from .vec_video_recorder import VecVideoRecorder
+
+@pytest.mark.parametrize('klass', (DummyVecEnv, ShmemVecEnv, SubprocVecEnv))
+@pytest.mark.parametrize('num_envs', (1, 4))
+@pytest.mark.parametrize('video_length', (10, 100))
+@pytest.mark.parametrize('video_interval', (1, 50))
+def test_video_recorder(klass, num_envs, video_length, video_interval):
+    """
+    Wrap an existing VecEnv with VevVideoRecorder,
+    Make (video_interval + video_length + 1) steps,
+    then check that the file is present
+    """
+
+    def make_fn():
+        env = gym.make('PongNoFrameskip-v4')
+        return env
+    fns = [make_fn for _ in range(num_envs)]
+    env = klass(fns)
+
+    with tempfile.TemporaryDirectory() as video_path:
+        env = VecVideoRecorder(env, video_path, record_video_trigger=lambda x: x % video_interval == 0, video_length=video_length)
+
+        env.reset()
+        for _ in range(video_interval + video_length + 1):
+            env.step([0] * num_envs)
+        env.close()
+
+
+        recorded_video = glob.glob(os.path.join(video_path, "*.mp4"))
+
+        # first and second step
+        assert len(recorded_video) == 2
+        # Files are not empty
+        assert all(os.stat(p).st_size != 0 for p in recorded_video)
+
+

baselines/common/vec_env/vec_video_recorder.py

@@ -0,0 +1,89 @@
+import os
+from baselines import logger
+from baselines.common.vec_env import VecEnvWrapper
+from gym.wrappers.monitoring import video_recorder
+
+
+class VecVideoRecorder(VecEnvWrapper):
+    """
+    Wrap VecEnv to record rendered image as mp4 video.
+    """
+
+    def __init__(self, venv, directory, record_video_trigger, video_length=200):
+        """
+        # Arguments
+            venv: VecEnv to wrap
+            directory: Where to save videos
+            record_video_trigger:
+                Function that defines when to start recording.
+                The function takes the current number of step,
+                and returns whether we should start recording or not.
+            video_length: Length of recorded video
+        """
+
+        VecEnvWrapper.__init__(self, venv)
+        self.record_video_trigger = record_video_trigger
+        self.video_recorder = None
+
+        self.directory = os.path.abspath(directory)
+        if not os.path.exists(self.directory): os.mkdir(self.directory)
+
+        self.file_prefix = "vecenv"
+        self.file_infix = '{}'.format(os.getpid())
+        self.step_id = 0
+        self.video_length = video_length
+
+        self.recording = False
+        self.recorded_frames = 0
+
+    def reset(self):
+        obs = self.venv.reset()
+
+        self.start_video_recorder()
+
+        return obs
+
+    def start_video_recorder(self):
+        self.close_video_recorder()
+
+        base_path = os.path.join(self.directory, '{}.video.{}.video{:06}'.format(self.file_prefix, self.file_infix, self.step_id))
+        self.video_recorder = video_recorder.VideoRecorder(
+                env=self.venv,
+                base_path=base_path,
+                metadata={'step_id': self.step_id}
+                )
+
+        self.video_recorder.capture_frame()
+        self.recorded_frames = 1
+        self.recording = True
+
+    def _video_enabled(self):
+        return self.record_video_trigger(self.step_id)
+
+    def step_wait(self):
+        obs, rews, dones, infos = self.venv.step_wait()
+
+        self.step_id += 1
+        if self.recording:
+            self.video_recorder.capture_frame()
+            self.recorded_frames += 1
+            if self.recorded_frames > self.video_length:
+                logger.info("Saving video to ", self.video_recorder.path)
+                self.close_video_recorder()
+        elif self._video_enabled():
+                self.start_video_recorder()
+
+        return obs, rews, dones, infos
+
+    def close_video_recorder(self):
+        if self.recording:
+            self.video_recorder.close()
+        self.recording = False
+        self.recorded_frames = 0
+
+    def close(self):
+        VecEnvWrapper.close(self)
+        self.close_video_recorder()
+
+    def __del__(self):
+        self.close()

baselines/ddpg/ddpg.py

@@ -12,8 +12,11 @@ import baselines.common.tf_util as U
 
 from baselines import logger
 import numpy as np
-from mpi4py import MPI
 
+try:
+    from mpi4py import MPI
+except ImportError:
+    MPI = None
 
 def learn(network, env,
           seed=None,
@@ -49,7 +52,11 @@ def learn(network, env,
     else:
         nb_epochs = 500
 
-    rank = MPI.COMM_WORLD.Get_rank()
+    if MPI is not None:
+        rank = MPI.COMM_WORLD.Get_rank()
+    else:
+        rank = 0
+
     nb_actions = env.action_space.shape[-1]
     assert (np.abs(env.action_space.low) == env.action_space.high).all()  # we assume symmetric actions.
 
@@ -59,7 +66,6 @@ def learn(network, env,
 
     action_noise = None
     param_noise = None
-    nb_actions = env.action_space.shape[-1]
     if noise_type is not None:
         for current_noise_type in noise_type.split(','):
             current_noise_type = current_noise_type.strip()
@@ -200,7 +206,11 @@ def learn(network, env,
                             eval_episode_rewards_history.append(eval_episode_reward[d])
                             eval_episode_reward[d] = 0.0
 
-        mpi_size = MPI.COMM_WORLD.Get_size()
+        if MPI is not None:
+            mpi_size = MPI.COMM_WORLD.Get_size()
+        else:
+            mpi_size = 1
+
         # Log stats.
         # XXX shouldn't call np.mean on variable length lists
         duration = time.time() - start_time
@@ -234,7 +244,10 @@ def learn(network, env,
             else:
                 raise ValueError('expected scalar, got %s'%x)
 
-        combined_stats_sums = MPI.COMM_WORLD.allreduce(np.array([ np.array(x).flatten()[0] for x in combined_stats.values()]))
+        combined_stats_sums = np.array([ np.array(x).flatten()[0] for x in combined_stats.values()])
+        if MPI is not None:
+            combined_stats_sums = MPI.COMM_WORLD.allreduce(combined_stats_sums)
+
         combined_stats = {k : v / mpi_size for (k,v) in zip(combined_stats.keys(), combined_stats_sums)}
 
         # Total statistics.

baselines/ddpg/ddpg_learner.py

@@ -9,7 +9,10 @@ from baselines import logger
 from baselines.common.mpi_adam import MpiAdam
 import baselines.common.tf_util as U
 from baselines.common.mpi_running_mean_std import RunningMeanStd
-from mpi4py import MPI
+try:
+    from mpi4py import MPI
+except ImportError:
+    MPI = None
 
 def normalize(x, stats):
     if stats is None:
@@ -64,7 +67,6 @@ class DDPG(object):
     def __init__(self, actor, critic, memory, observation_shape, action_shape, param_noise=None, action_noise=None,
         gamma=0.99, tau=0.001, normalize_returns=False, enable_popart=False, normalize_observations=True,
         batch_size=128, observation_range=(-5., 5.), action_range=(-1., 1.), return_range=(-np.inf, np.inf),
-        adaptive_param_noise=True, adaptive_param_noise_policy_threshold=.1,
         critic_l2_reg=0., actor_lr=1e-4, critic_lr=1e-3, clip_norm=None, reward_scale=1.):
         # Inputs.
         self.obs0 = tf.placeholder(tf.float32, shape=(None,) + observation_shape, name='obs0')
@@ -268,7 +270,7 @@ class DDPG(object):
 
         if self.action_noise is not None and apply_noise:
             noise = self.action_noise()
-            assert noise.shape == action.shape
+            assert noise.shape == action[0].shape
             action += noise
         action = np.clip(action, self.action_range[0], self.action_range[1])
 
@@ -358,6 +360,11 @@ class DDPG(object):
         return stats
 
     def adapt_param_noise(self):
+        try:
+            from mpi4py import MPI
+        except ImportError:
+            MPI = None
+
         if self.param_noise is None:
             return 0.
 
@@ -371,7 +378,16 @@ class DDPG(object):
             self.param_noise_stddev: self.param_noise.current_stddev,
         })
 
-        mean_distance = MPI.COMM_WORLD.allreduce(distance, op=MPI.SUM) / MPI.COMM_WORLD.Get_size()
+        if MPI is not None:
+            mean_distance = MPI.COMM_WORLD.allreduce(distance, op=MPI.SUM) / MPI.COMM_WORLD.Get_size()
+        else:
+            mean_distance = distance
+
+        if MPI is not None:
+            mean_distance = MPI.COMM_WORLD.allreduce(distance, op=MPI.SUM) / MPI.COMM_WORLD.Get_size()
+        else:
+            mean_distance = distance
+
         self.param_noise.adapt(mean_distance)
         return mean_distance
 

baselines/deepq/build_graph.py

@@ -33,7 +33,7 @@ The functions in this file can are used to create the following functions:
     stochastic: bool
         if set to False all the actions are always deterministic (default False)
     update_eps_ph: float
-        update epsilon a new value, if negative not update happens
+        update epsilon to a new value, if negative no update happens
         (default: no update)
     reset_ph: bool
         reset the perturbed policy by sampling a new perturbation

baselines/deepq/models.py

@@ -2,9 +2,9 @@ import tensorflow as tf
 import tensorflow.contrib.layers as layers
 
 
-def _mlp(hiddens, inpt, num_actions, scope, reuse=False, layer_norm=False):
+def _mlp(hiddens, input_, num_actions, scope, reuse=False, layer_norm=False):
     with tf.variable_scope(scope, reuse=reuse):
-        out = inpt
+        out = input_
         for hidden in hiddens:
             out = layers.fully_connected(out, num_outputs=hidden, activation_fn=None)
             if layer_norm:
@@ -30,9 +30,9 @@ def mlp(hiddens=[], layer_norm=False):
     return lambda *args, **kwargs: _mlp(hiddens, layer_norm=layer_norm, *args, **kwargs)
 
 
-def _cnn_to_mlp(convs, hiddens, dueling, inpt, num_actions, scope, reuse=False, layer_norm=False):
+def _cnn_to_mlp(convs, hiddens, dueling, input_, num_actions, scope, reuse=False, layer_norm=False):
     with tf.variable_scope(scope, reuse=reuse):
-        out = inpt
+        out = input_
         with tf.variable_scope("convnet"):
             for num_outputs, kernel_size, stride in convs:
                 out = layers.convolution2d(out,

baselines/logger.py

@@ -54,7 +54,7 @@ class HumanOutputFormat(KVWriter, SeqWriter):
         # Write out the data
         dashes = '-' * (keywidth + valwidth + 7)
         lines = [dashes]
-        for (key, val) in sorted(key2str.items()):
+        for (key, val) in sorted(key2str.items(), key=lambda kv: kv[0].lower()):
             lines.append('| %s%s | %s%s |' % (
                 key,
                 ' ' * (keywidth - len(key)),

baselines/ppo2/defaults.py

@@ -20,3 +20,6 @@ def atari():
         lr=lambda f : f * 2.5e-4,
         cliprange=lambda f : f * 0.1,
     )
+
+def retro():
+    return atari()

baselines/ppo2/microbatched_model.py

@@ -0,0 +1,76 @@
+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):
+
+        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)
+
+        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)
+
+        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, 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)
+
+        # Initialize empty list for per-microbatch stats like pg_loss, vf_loss, entropy, approxkl (whatever is in self.stats_list)
+        stats_vs = []
+
+        for microbatch_idx in range(self.nmicrobatches):
+            _sli = range(microbatch_idx * self.microbatch_size, (microbatch_idx+1) * self.microbatch_size)
+            td_map = {
+                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]
+            }
+
+            # 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)
+            if microbatch_idx == 0:
+                sum_grad_v = grad_v
+            else:
+                # .. and add to the total of the gradients
+                for i, g in enumerate(grad_v):
+                    sum_grad_v[i] += g
+            stats_vs.append(stats_v)
+
+        feed_dict = {ph: sum_g / self.nmicrobatches for ph, sum_g in zip(self.grads_ph, sum_grad_v)}
+        feed_dict[self.LR] = lr
+        # Update variables using average of the gradients
+        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

@@ -0,0 +1,157 @@
+import tensorflow as tf
+import functools
+
+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
+    from mpi4py import MPI
+    from baselines.common.mpi_util import sync_from_root
+except ImportError:
+    MPI = None
+
+class Model(object):
+    """
+    We use this object to :
+    __init__:
+    - Creates the step_model
+    - Creates the train_model
+
+    train():
+    - Make the training part (feedforward and retropropagation of gradients)
+
+    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, microbatch_size=None):
+        self.sess = sess = get_session()
+
+        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)
+
+            # Train model for training
+            if microbatch_size is None:
+                train_model = policy(nbatch_train, nsteps, sess)
+            else:
+                train_model = policy(microbatch_size, nsteps, sess)
+
+        # 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, [])
+
+        neglogpac = train_model.pd.neglogp(A)
+
+        # 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())
+
+        # CALCULATE THE LOSS
+        # Total loss = Policy gradient loss - entropy * entropy coefficient + Value coefficient * value loss
+
+        # 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)
+
+        vf_loss = .5 * tf.reduce_mean(tf.maximum(vf_losses1, vf_losses2))
+
+        # Calculate ratio (pi current policy / pi old policy)
+        ratio = tf.exp(OLDNEGLOGPAC - neglogpac)
+
+        # Defining Loss = - J is equivalent to max J
+        pg_losses = -ADV * ratio
+
+        pg_losses2 = -ADV * tf.clip_by_value(ratio, 1.0 - CLIPRANGE, 1.0 + CLIPRANGE)
+
+        # 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)))
+
+        # Total loss
+        loss = pg_loss - entropy * ent_coef + vf_loss * vf_coef
+
+        # 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)
+
+        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.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.step = act_model.step
+        self.value = act_model.value
+        self.initial_state = act_model.initial_state
+
+        self.save = functools.partial(save_variables, sess=sess)
+        self.load = functools.partial(load_variables, sess=sess)
+
+        if MPI is None or MPI.COMM_WORLD.Get_rank() == 0:
+            initialize()
+        else:
+            global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="")
+            sync_from_root(sess, global_variables) #pylint: disable=E1101
+
+    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
+
+        # Normalize the advantages
+        advs = (advs - advs.mean()) / (advs.std() + 1e-8)
+
+        td_map = {
+            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
+        }
+        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/ppo2.py

@@ -1,217 +1,17 @@
 import os
 import time
-import functools
 import numpy as np
 import os.path as osp
-import tensorflow as tf
 from baselines import logger
 from collections import deque
 from baselines.common import explained_variance, set_global_seeds
 from baselines.common.policies import build_policy
-from baselines.common.runners import AbstractEnvRunner
+try:
-from baselines.common.tf_util import get_session, save_variables, load_variables
+    from mpi4py import MPI
-from baselines.common.mpi_adam_optimizer import MpiAdamOptimizer
+except ImportError:
+    MPI = None
+from baselines.ppo2.runner import Runner
 
-from mpi4py import MPI
-from baselines.common.tf_util import initialize
-from baselines.common.mpi_util import sync_from_root
-
-class Model(object):
-    """
-    We use this object to :
-    __init__:
-    - Creates the step_model
-    - Creates the train_model
-
-    train():
-    - Make the training part (feedforward and retropropagation of gradients)
-
-    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):
-        sess = get_session()
-
-        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)
-
-            # Train model for training
-            train_model = policy(nbatch_train, nsteps, sess)
-
-        # CREATE THE PLACEHOLDERS
-        A = train_model.pdtype.sample_placeholder([None])
-        ADV = tf.placeholder(tf.float32, [None])
-        R = tf.placeholder(tf.float32, [None])
-        # Keep track of old actor
-        OLDNEGLOGPAC = tf.placeholder(tf.float32, [None])
-        # Keep track of old critic
-        OLDVPRED = tf.placeholder(tf.float32, [None])
-        LR = tf.placeholder(tf.float32, [])
-        # Cliprange
-        CLIPRANGE = tf.placeholder(tf.float32, [])
-
-        neglogpac = train_model.pd.neglogp(A)
-
-        # 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())
-
-        # CALCULATE THE LOSS
-        # Total loss = Policy gradient loss - entropy * entropy coefficient + Value coefficient * value loss
-
-        # 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)
-
-        vf_loss = .5 * tf.reduce_mean(tf.maximum(vf_losses1, vf_losses2))
-
-        # Calculate ratio (pi current policy / pi old policy)
-        ratio = tf.exp(OLDNEGLOGPAC - neglogpac)
-
-        # Defining Loss = - J is equivalent to max J
-        pg_losses = -ADV * ratio
-
-        pg_losses2 = -ADV * tf.clip_by_value(ratio, 1.0 - CLIPRANGE, 1.0 + CLIPRANGE)
-
-        # 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)))
-
-        # Total loss
-        loss = pg_loss - entropy * ent_coef + vf_loss * vf_coef
-
-        # UPDATE THE PARAMETERS USING LOSS
-        # 1. Get the model parameters
-        params = tf.trainable_variables('ppo2_model')
-        # 2. Build our trainer
-        trainer = MpiAdamOptimizer(MPI.COMM_WORLD, learning_rate=LR, epsilon=1e-5)
-        # 3. Calculate the gradients
-        grads_and_var = trainer.compute_gradients(loss, params)
-        grads, var = zip(*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
-
-        _train = trainer.apply_gradients(grads_and_var)
-
-        def train(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
-
-            # Normalize the advantages
-            advs = (advs - advs.mean()) / (advs.std() + 1e-8)
-            td_map = {train_model.X:obs, A:actions, ADV:advs, R:returns, LR:lr,
-                    CLIPRANGE:cliprange, OLDNEGLOGPAC:neglogpacs, OLDVPRED:values}
-            if states is not None:
-                td_map[train_model.S] = states
-                td_map[train_model.M] = masks
-            return sess.run(
-                [pg_loss, vf_loss, entropy, approxkl, clipfrac, _train],
-                td_map
-            )[:-1]
-        self.loss_names = ['policy_loss', 'value_loss', 'policy_entropy', 'approxkl', 'clipfrac']
-
-
-        self.train = train
-        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
-
-        self.save = functools.partial(save_variables, sess=sess)
-        self.load = functools.partial(load_variables, sess=sess)
-
-        if MPI.COMM_WORLD.Get_rank() == 0:
-            initialize()
-        global_variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope="")
-        sync_from_root(sess, global_variables) #pylint: disable=E1101
-
-class Runner(AbstractEnvRunner):
-    """
-    We use this object to make a mini batch of experiences
-    __init__:
-    - Initialize the runner
-
-    run():
-    - Make a mini batch
-    """
-    def __init__(self, *, env, model, nsteps, gamma, lam):
-        super().__init__(env=env, model=model, nsteps=nsteps)
-        # Lambda used in GAE (General Advantage Estimation)
-        self.lam = lam
-        # Discount rate
-        self.gamma = gamma
-
-    def run(self):
-        # 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):
-            # 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[:], rewards, self.dones, infos = self.env.step(actions)
-            for info in infos:
-                maybeepinfo = info.get('episode')
-                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)
-
-        # 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 t == self.nsteps - 1:
-                nextnonterminal = 1.0 - self.dones
-                nextvalues = last_values
-            else:
-                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:])
 
 def constfn(val):
     def f(_):
@@ -221,7 +21,7 @@ def constfn(val):
 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, **network_kwargs):
+            save_interval=0, load_path=None, model_fn=None, **network_kwargs):
     '''
     Learn policy using PPO algorithm (https://arxiv.org/abs/1707.06347)
 
@@ -299,10 +99,14 @@ def learn(*, network, env, total_timesteps, eval_env = None, seed=None, nsteps=2
     nbatch_train = nbatch // nminibatches
 
     # Instantiate the model object (that creates act_model and train_model)
-    make_model = lambda : Model(policy=policy, ob_space=ob_space, ac_space=ac_space, nbatch_act=nenvs, nbatch_train=nbatch_train,
+    if model_fn is None:
+        from baselines.ppo2.model import Model
+        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)
-    model = make_model()
+
     if load_path is not None:
         model.load(load_path)
     # Instantiate the runner object
@@ -310,8 +114,6 @@ def learn(*, network, env, total_timesteps, eval_env = None, seed=None, nsteps=2
     if eval_env is not None:
         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)
@@ -392,9 +194,9 @@ def learn(*, network, env, total_timesteps, eval_env = None, seed=None, nsteps=2
             logger.logkv('time_elapsed', tnow - tfirststart)
             for (lossval, lossname) in zip(lossvals, model.loss_names):
                 logger.logkv(lossname, lossval)
-            if MPI.COMM_WORLD.Get_rank() == 0:
+            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.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)

baselines/ppo2/runner.py

@@ -0,0 +1,76 @@
+import numpy as np
+from baselines.common.runners import AbstractEnvRunner
+
+class Runner(AbstractEnvRunner):
+    """
+    We use this object to make a mini batch of experiences
+    __init__:
+    - Initialize the runner
+
+    run():
+    - Make a mini batch
+    """
+    def __init__(self, *, env, model, nsteps, gamma, lam):
+        super().__init__(env=env, model=model, nsteps=nsteps)
+        # Lambda used in GAE (General Advantage Estimation)
+        self.lam = lam
+        # Discount rate
+        self.gamma = gamma
+
+    def run(self):
+        # 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):
+            # 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[:], rewards, self.dones, infos = self.env.step(actions)
+            for info in infos:
+                maybeepinfo = info.get('episode')
+                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)
+
+        # 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 t == self.nsteps - 1:
+                nextnonterminal = 1.0 - self.dones
+                nextvalues = last_values
+            else:
+                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

@@ -0,0 +1,34 @@
+import gym
+import tensorflow as tf
+import numpy as np
+from functools import partial
+
+from baselines.common.vec_env.dummy_vec_env import DummyVecEnv
+from baselines.common.tf_util import make_session
+from baselines.ppo2.ppo2 import learn
+
+from baselines.ppo2.microbatched_model import MicrobatchedModel
+
+def test_microbatches():
+    def env_fn():
+        env = gym.make('CartPole-v0')
+        env.seed(0)
+        return env
+
+    learn_fn = partial(learn, network='mlp', nsteps=32, total_timesteps=32, seed=0)
+
+    env_ref = DummyVecEnv([env_fn])
+    sess_ref = make_session(make_default=True, graph=tf.Graph())
+    learn_fn(env=env_ref)
+    vars_ref = {v.name: sess_ref.run(v) for v in tf.trainable_variables()}
+
+    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))
+    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=1e-3)
+
+if __name__ == '__main__':
+    test_microbatches()

baselines/run.py

@@ -6,6 +6,7 @@ from collections import defaultdict
 import tensorflow as tf
 import numpy as np
 
+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
@@ -62,6 +63,8 @@ def train(args, extra_args):
     alg_kwargs.update(extra_args)
 
     env = build_env(args)
+    if args.save_video_interval != 0:
+        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

baselines/trpo_mpi/trpo_mpi.py

@@ -4,7 +4,6 @@ import baselines.common.tf_util as U
 import tensorflow as tf, numpy as np
 import time
 from baselines.common import colorize
-from mpi4py import MPI
 from collections import deque
 from baselines.common import set_global_seeds
 from baselines.common.mpi_adam import MpiAdam
@@ -13,6 +12,11 @@ from baselines.common.input import observation_placeholder
 from baselines.common.policies import build_policy
 from contextlib import contextmanager
 
+try:
+    from mpi4py import MPI
+except ImportError:
+    MPI = None
+
 def traj_segment_generator(pi, env, horizon, stochastic):
     # Initialize state variables
     t = 0
@@ -146,9 +150,12 @@ def learn(*,
 
     '''
 
-
+    if MPI is not None:
-    nworkers = MPI.COMM_WORLD.Get_size()
+        nworkers = MPI.COMM_WORLD.Get_size()
-    rank = MPI.COMM_WORLD.Get_rank()
+        rank = MPI.COMM_WORLD.Get_rank()
+    else:
+        nworkers = 1
+        rank = 0
 
     cpus_per_worker = 1
     U.get_session(config=tf.ConfigProto(
@@ -237,9 +244,13 @@ def learn(*,
 
     def allmean(x):
         assert isinstance(x, np.ndarray)
-        out = np.empty_like(x)
+        if MPI is not None:
-        MPI.COMM_WORLD.Allreduce(x, out, op=MPI.SUM)
+            out = np.empty_like(x)
-        out /= nworkers
+            MPI.COMM_WORLD.Allreduce(x, out, op=MPI.SUM)
+            out /= nworkers
+        else:
+            out = np.copy(x)
+
         return out
 
     U.initialize()
@@ -247,7 +258,9 @@ def learn(*,
         pi.load(load_path)
 
     th_init = get_flat()
-    MPI.COMM_WORLD.Bcast(th_init, root=0)
+    if MPI is not None:
+        MPI.COMM_WORLD.Bcast(th_init, root=0)
+
     set_from_flat(th_init)
     vfadam.sync()
     print("Init param sum", th_init.sum(), flush=True)
@@ -260,8 +273,8 @@ def learn(*,
     timesteps_so_far = 0
     iters_so_far = 0
     tstart = time.time()
-    lenbuffer = deque(maxlen=40) # rolling buffer for episode lengths
+    lenbuffer = deque(maxlen=100) # rolling buffer for episode lengths
-    rewbuffer = deque(maxlen=40) # rolling buffer for episode rewards
+    rewbuffer = deque(maxlen=100) # rolling buffer for episode rewards
 
     if sum([max_iters>0, total_timesteps>0, max_episodes>0])==0:
         # noththing to be done
@@ -353,7 +366,11 @@ def learn(*,
         logger.record_tabular("ev_tdlam_before", explained_variance(vpredbefore, tdlamret))
 
         lrlocal = (seg["ep_lens"], seg["ep_rets"]) # local values
-        listoflrpairs = MPI.COMM_WORLD.allgather(lrlocal) # list of tuples
+        if MPI is not None:
+            listoflrpairs = MPI.COMM_WORLD.allgather(lrlocal) # list of tuples
+        else:
+            listoflrpairs = [lrlocal]
+
         lens, rews = map(flatten_lists, zip(*listoflrpairs))
         lenbuffer.extend(lens)
         rewbuffer.extend(rews)

setup.py

@@ -11,10 +11,14 @@ extras = {
     'test': [
         'filelock',
         'pytest',
+        'pytest-forked',
         'atari-py'
     ],
     'bullet': [
         'pybullet',
+    ],
+    'mpi': [
+        'mpi4py'
     ]
 }
 
@@ -34,7 +38,6 @@ setup(name='baselines',
           'joblib',
           'dill',
           'progressbar2',
-          'mpi4py',
           'cloudpickle',
           'click',
           'opencv-python'