ddpg.py 文件源码

def __init__(self, sess, state_size, action_size,
                 batch_size, tau, learning_rate):
        """Init critic network."""
        self.sess = sess
        self.batch_size = batch_size
        self.tau = tau
        self.learning_rate = learning_rate
        self.action_size = action_size

        K.set_session(sess)

        self.model, self.action, self.state = \
            self.create_critic_network(state_size, action_size)
        self.target_model, self.target_action, self.target_state = \
            self.create_critic_network(state_size, action_size)
        self.action_grads = tf.gradients(self.model.output, self.action)
        self.sess.run(tf.initialize_all_variables())