Merge pull request #120 from hamzamerzic/tensorflow_global_variable

Deprecated VARIABLES -> GLOBAL_VARIABLES.

baselines/ppo1/cnn_policy.py

@@ -18,7 +18,7 @@ class CnnPolicy(object):
         sequence_length = None
 
         ob = U.get_placeholder(name="ob", dtype=tf.float32, shape=[sequence_length] + list(ob_space.shape))
-    
+
         x = ob / 255.0
         if kind == 'small': # from A3C paper
             x = tf.nn.relu(U.conv2d(x, 16, "l1", [8, 8], [4, 4], pad="VALID"))
@@ -49,7 +49,7 @@ class CnnPolicy(object):
         ac1, vpred1 =  self._act(stochastic, ob[None])
         return ac1[0], vpred1[0]
     def get_variables(self):
-        return tf.get_collection(tf.GraphKeys.VARIABLES, self.scope)
+        return tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, self.scope)
     def get_trainable_variables(self):
         return tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.scope)
     def get_initial_state(self):

baselines/ppo1/mlp_policy.py

@@ -18,7 +18,7 @@ class MlpPolicy(object):
         sequence_length = None
 
         ob = U.get_placeholder(name="ob", dtype=tf.float32, shape=[sequence_length] + list(ob_space.shape))
-        
+
         with tf.variable_scope("obfilter"):
             self.ob_rms = RunningMeanStd(shape=ob_space.shape)
 
@@ -27,12 +27,12 @@ class MlpPolicy(object):
         for i in range(num_hid_layers):
             last_out = tf.nn.tanh(U.dense(last_out, hid_size, "vffc%i"%(i+1), weight_init=U.normc_initializer(1.0)))
         self.vpred = U.dense(last_out, 1, "vffinal", weight_init=U.normc_initializer(1.0))[:,0]
-        
+
         last_out = obz
         for i in range(num_hid_layers):
             last_out = tf.nn.tanh(U.dense(last_out, hid_size, "polfc%i"%(i+1), weight_init=U.normc_initializer(1.0)))
         if gaussian_fixed_var and isinstance(ac_space, gym.spaces.Box):
-            mean = U.dense(last_out, pdtype.param_shape()[0]//2, "polfinal", U.normc_initializer(0.01))            
+            mean = U.dense(last_out, pdtype.param_shape()[0]//2, "polfinal", U.normc_initializer(0.01))
             logstd = tf.get_variable(name="logstd", shape=[1, pdtype.param_shape()[0]//2], initializer=tf.zeros_initializer())
             pdparam = U.concatenate([mean, mean * 0.0 + logstd], axis=1)
         else:
@@ -51,7 +51,7 @@ class MlpPolicy(object):
         ac1, vpred1 =  self._act(stochastic, ob[None])
         return ac1[0], vpred1[0]
     def get_variables(self):
-        return tf.get_collection(tf.GraphKeys.VARIABLES, self.scope)
+        return tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, self.scope)
     def get_trainable_variables(self):
         return tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.scope)
     def get_initial_state(self):

baselines/trpo_mpi/nosharing_cnn_policy.py

@@ -18,7 +18,7 @@ class CnnPolicy(object):
         sequence_length = None
 
         ob = U.get_placeholder(name="ob", dtype=tf.float32, shape=[sequence_length] + list(ob_space.shape))
-        
+
         obscaled = ob / 255.0
 
         with tf.variable_scope("pol"):
@@ -49,7 +49,7 @@ class CnnPolicy(object):
         ac1, vpred1 =  self._act(stochastic, ob[None])
         return ac1[0], vpred1[0]
     def get_variables(self):
-        return tf.get_collection(tf.GraphKeys.VARIABLES, self.scope)
+        return tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, self.scope)
     def get_trainable_variables(self):
         return tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.scope)
     def get_initial_state(self):