merged master

baselines/common/distributions.py

@@ -75,7 +75,8 @@ class CategoricalPdType(PdType):
 
 class MultiCategoricalPdType(PdType):
     def __init__(self, nvec):
-        self.ncats = nvec
+        self.ncats = nvec.astype('int32')
+        assert (self.ncats > 0).all()
     def pdclass(self):
         return MultiCategoricalPd
     def pdfromflat(self, flat):

baselines/common/tests/test_tf_util.py

@@ -18,7 +18,9 @@ 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/util.py

@@ -12,47 +12,33 @@ def simple_test(env_fn, learn_fn, min_reward_fraction, n_trials=N_TRIALS):
         return env
 
     np.random.seed(0)
-
     env = DummyVecEnv([seeded_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, \
@@ -62,14 +48,12 @@ 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
         episode_rew = []
         episode_actions = []
         episode_obs = []
-
         while True:
             if state is not None:
                 a, v, state, _ = model.step(obs, S=state, M=[False])
@@ -77,17 +61,13 @@ 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

@@ -185,6 +185,7 @@ 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]
@@ -196,15 +197,17 @@ class _Function(object):
         else:
             feed_dict[inpt] = adjust_shape(inpt, value)
 
-    def __call__(self, *args):
-        assert len(args) <= len(self.inputs), "Too many arguments provided"
+    def __call__(self, *args, **kwargs):
+        assert len(args) + len(kwargs) <= len(self.inputs), "Too many arguments provided"
         feed_dict = {}
-        # Update the args
-        for inpt, value in zip(self.inputs, args):
-            self._feed_input(feed_dict, inpt, value)
         # 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)
         results = get_session().run(self.outputs_update, feed_dict=feed_dict)[:-1]
         return results
 

baselines/ppo2/test_microbatches.py

@@ -25,10 +25,11 @@ 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=1e-3)
+        np.testing.assert_allclose(vars_ref[v], vars_test[v], atol=3e-3)
 
 if __name__ == '__main__':
     test_microbatches()