ddpg.py 文件源码

def setup_critic_optimizer(self):
        logger.info('setting up critic optimizer')
        normalized_critic_target_tf = tf.clip_by_value(normalize(self.critic_target, self.ret_rms), self.return_range[0], self.return_range[1])
        self.critic_loss = tf.reduce_mean(tf.square(self.normalized_critic_tf - normalized_critic_target_tf))
        if self.critic_l2_reg > 0.:
            critic_reg_vars = [var for var in self.critic.trainable_vars if 'kernel' in var.name and 'output' not in var.name]
            for var in critic_reg_vars:
                logger.info('  regularizing: {}'.format(var.name))
            logger.info('  applying l2 regularization with {}'.format(self.critic_l2_reg))
            critic_reg = tc.layers.apply_regularization(
                tc.layers.l2_regularizer(self.critic_l2_reg),
                weights_list=critic_reg_vars
            )
            self.critic_loss += critic_reg
        critic_shapes = [var.get_shape().as_list() for var in self.critic.trainable_vars]
        critic_nb_params = sum([reduce(lambda x, y: x * y, shape) for shape in critic_shapes])
        logger.info('  critic shapes: {}'.format(critic_shapes))
        logger.info('  critic params: {}'.format(critic_nb_params))
        self.critic_grads = U.flatgrad(self.critic_loss, self.critic.trainable_vars, clip_norm=self.clip_norm)
        self.critic_optimizer = MpiAdam(var_list=self.critic.trainable_vars,
            beta1=0.9, beta2=0.999, epsilon=1e-08)