Merge branch 'master' of github.com:openai/baselines into internal

README.md

@@ -1,3 +1,5 @@
+**Status:** Active (under active development, breaking changes may occur)
+
 <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)
 
 # Baselines

baselines/common/atari_wrappers.py

@@ -72,8 +72,8 @@ class EpisodicLifeEnv(gym.Wrapper):
         # then update lives to handle bonus lives
         lives = self.env.unwrapped.ale.lives()
         if lives < self.lives and lives > 0:
-            # for Qbert sometimes we stay in lives == 0 condtion for a few frames
-            # so its important to keep lives > 0, so that we only reset once
+            # for Qbert sometimes we stay in lives == 0 condition for a few frames
+            # so it's important to keep lives > 0, so that we only reset once
             # the environment advertises done.
             done = True
         self.lives = lives

baselines/ddpg/ddpg_learner.py

@@ -185,7 +185,7 @@ class DDPG(object):
         normalized_critic_target_tf = tf.clip_by_value(normalize(self.critic_target, self.ret_rms), self.return_range[0], self.return_range[1])
         self.critic_loss = tf.reduce_mean(tf.square(self.normalized_critic_tf - normalized_critic_target_tf))
         if self.critic_l2_reg > 0.:
-            critic_reg_vars = [var for var in self.critic.trainable_vars if 'kernel' in var.name and 'output' not in var.name]
+            critic_reg_vars = [var for var in self.critic.trainable_vars if var.name.endswith('/w:0') and 'output' not in var.name]
             for var in critic_reg_vars:
                 logger.info('  regularizing: {}'.format(var.name))
             logger.info('  applying l2 regularization with {}'.format(self.critic_l2_reg))

baselines/ddpg/models.py

@@ -42,7 +42,7 @@ class Critic(Model):
         with tf.variable_scope(self.name, reuse=tf.AUTO_REUSE):
             x = tf.concat([obs, action], axis=-1) # this assumes observation and action can be concatenated
             x = self.network_builder(x)
-            x = tf.layers.dense(x, 1, kernel_initializer=tf.random_uniform_initializer(minval=-3e-3, maxval=3e-3))
+            x = tf.layers.dense(x, 1, kernel_initializer=tf.random_uniform_initializer(minval=-3e-3, maxval=3e-3), name='output')
         return x
 
     @property

baselines/deepq/__init__.py

@@ -5,4 +5,4 @@ from baselines.deepq.replay_buffer import ReplayBuffer, PrioritizedReplayBuffer
 
 def wrap_atari_dqn(env):
     from baselines.common.atari_wrappers import wrap_deepmind
-    return wrap_deepmind(env, frame_stack=True, scale=True)
+    return wrap_deepmind(env, frame_stack=True, scale=False)