DDPG.py 文件源码

def __init__(self, sess, action_dim, action_bound, learning_rate, t_replace_iter):
        self.sess = sess
        self.a_dim = action_dim
        self.action_bound = action_bound
        self.lr = learning_rate
        self.t_replace_iter = t_replace_iter
        self.t_replace_counter = 0

        with tf.variable_scope('Actor'):
            # input s, output a
            self.a = self._build_net(S, scope='eval_net', trainable=True)

            # input s_, output a, get a_ for critic
            self.a_ = self._build_net(S_, scope='target_net', trainable=False)

        self.e_params = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='Actor/eval_net')
        self.t_params = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='Actor/target_net')