critic.py 文件源码

def build_train(self):
        self.op_rewards = tf.placeholder(tf.float32, [None])

        self.variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=tf.get_variable_scope().name)
        regularization = tf.contrib.layers.apply_regularization(
            tf.contrib.layers.l2_regularizer(0.01),
            self.variables,
        )
        self.op_loss = tf.reduce_mean((self.op_rewards - self.op_critic)**2) + regularization
        self.op_summary = tf.merge_summary([
            tf.scalar_summary("critic loss", self.op_loss),
            tf.histogram_summary("critic", self.op_critic),
        ])

        self.op_grad_actions = tf.gradients(self.op_critic, self.op_actions)[0]
        self.op_train = tf.train.AdamOptimizer(self.learning_rate).minimize(self.op_loss)