hh

code/Agent_algorithm.py

@@ -9,8 +9,7 @@ from metrics import update_metric, update_speaker_prob, update_listener_prob, up
 
 # hyperparameters
 MAX_EP = 10000000   # maximum count of training data
-A_LR = 0.002        # learning rate for actor
-C_LR = 0.002        # learning rate for critic
+LR = 0.002        # learning rate
 BATCH_SIZE = 128
 EPSILON = 0.2
 CLIP = 0.2
@@ -76,7 +75,7 @@ class Speaker(object):
         surrogate = ratio * self.tf_reward
 
         self.loss = -tf.reduce_mean(tf.minimum(surrogate, tf.clip_by_value(ratio, 1. - CLIP, 1. + CLIP) * self.tf_reward))
-        self.train = tf.train.AdamOptimizer(A_LR).minimize(self.loss, var_list = [speak_params])
+        self.train = tf.train.AdamOptimizer(LR).minimize(self.loss, var_list = [speak_params])
 
         self.sess.run(tf.global_variables_initializer())
 
@@ -215,7 +214,7 @@ class Listener(object):
         surrogate = ratio * self.tf_reward
 
         self.loss = -tf.reduce_mean(tf.minimum(surrogate, tf.clip_by_value(ratio, 1. - CLIP, 1. + CLIP) * self.tf_reward))
-        self.train = tf.train.AdamOptimizer(A_LR).minimize(self.loss, var_list = [listen_params])
+        self.train = tf.train.AdamOptimizer(LR).minimize(self.loss, var_list = [listen_params])
 
         self.sess.run(tf.global_variables_initializer())