Twin Delayed Multi-Agent Deep Deterministic Policy Gradient

Mengying Zhan, Jinchao Chen, Chenglie Du, Yuxin Duan

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

Recently, reinforcement learning has made remarkable achievements in the fields of natural science, engineering, medicine and operational research. Reinforcement learning addresses sequence problems and considers long-term returns. This long-term view of reinforcement learning is critical to find the optimal solution of many problems. The existing multi- agent reinforcement learning algorithms have the problem of overestimation in estimating the Q value. Unfortunately, there have not been many studies on overestimation of agent reinforcement learning, which will affect the learning efficiency of reinforcement learning. Based on the traditional multi-agent reinforcement learning algorithm, this paper improves the actor network and critic network, optimizes the overestimation of Q value and adopts the update delayed method to make the actor training more stable. In order to test the effectiveness of the algorithm structure, the modified method is compared with the traditional MADDPG, DDPG and DQN methods in the simulation environment.

源语言英语
主期刊名Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021
编辑Yinglin Wang, Zheying Zhang
出版商Institute of Electrical and Electronics Engineers Inc.
48-52
页数5
ISBN(电子版)9781665426558
DOI
出版状态已出版 - 2021
活动8th IEEE International Conference on Progress in Informatics and Computing, PIC 2021 - Virtual, Online, 中国
期限: 17 12月 202119 12月 2021

出版系列

姓名Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021

会议

会议8th IEEE International Conference on Progress in Informatics and Computing, PIC 2021
国家/地区中国
Virtual, Online
时期17/12/2119/12/21

指纹

探究 'Twin Delayed Multi-Agent Deep Deterministic Policy Gradient' 的科研主题。它们共同构成独一无二的指纹。

引用此