def __init__(self, sess, state_size, action_size, BATCH_SIZE, TAU, LEARNING_RATE):
self.sess = sess
self.BATCH_SIZE = BATCH_SIZE
self.TAU = TAU
self.LEARNING_RATE = LEARNING_RATE
K.set_session(sess)
#Now create the model
self.model , self.weights, self.state = self.create_actor_network(state_size, action_size)
self.target_model, self.target_weights, self.target_state = self.create_actor_network(state_size, action_size)
self.action_gradient = tf.placeholder(tf.float32,[None, action_size])
self.params_grad = tf.gradients(self.model.output, self.weights, -self.action_gradient)
grads = zip(self.params_grad, self.weights)
self.optimize = tf.train.AdamOptimizer(LEARNING_RATE).apply_gradients(grads)
self.sess.run(tf.global_variables_initializer())
ActorNetwork.py 文件源码
python
阅读 37
收藏 0
点赞 0
评论 0
评论列表
文章目录