深度强化学习综述

王浩楠, 刘苧, 章艺云, 冯大伟, 黄峰… - 信息与电子工程前沿 …, 2022 - fitee.zjujournals.com
… We provide a detailed review over stateof-the-art RL methods and … Otherwise, you can choose
the model-free off-policy algorithms that re… 3 shows the architecture of bootstrapped DQN. …