@inproceedings{dfdd0d890400415b8ae73abe0dc80bd2,
title = "Twin Delayed Multi-Agent Deep Deterministic Policy Gradient",
abstract = "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.",
keywords = "Deep learning, multi-agent system, neural networks, overestimation, Reinforcement learning",
author = "Mengying Zhan and Jinchao Chen and Chenglie Du and Yuxin Duan",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 8th IEEE International Conference on Progress in Informatics and Computing, PIC 2021 ; Conference date: 17-12-2021 Through 19-12-2021",
year = "2021",
doi = "10.1109/PIC53636.2021.9687069",
language = "英语",
series = "Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "48--52",
editor = "Yinglin Wang and Zheying Zhang",
booktitle = "Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021",
}