@inproceedings{51a3acd147ec48679130f422a7755cd5,
title = "Experience Replay Method with Attention for Multi-agent Reinforcement Learning",
abstract = "To enhance the efficiency of the experience replay method, this article proposes an improvement by incorporating the past experience reward value and the timing difference error (TD error) to form a prioritized R-T experience parameter. Additionally, an attention mechanism is introduced to determine data priority based on the R-T experience parameter. This improved experience replay method is then applied to the multi-agent deep deterministic policy gradient algorithm, resulting in improved algorithm training efficiency and stability.",
keywords = "Attention mechanism, Experience replay, Multi-agent system, Reinforcement learning",
author = "Jiashan Gao and Jinyu Xu and Xingjian Wang and Shaoping Wang and Zeling Pang",
note = "Publisher Copyright: {\textcopyright} 2024, Chinese Society of Aeronautics and Astronautics.; 6th China Aeronautical Science and Technology Conference, CASTC 2023 ; Conference date: 26-09-2023 Through 27-09-2023",
year = "2024",
doi = "10.1007/978-981-99-8864-8\_59",
language = "英语",
isbn = "9789819988631",
series = "Lecture Notes in Mechanical Engineering",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "615--621",
booktitle = "Proceedings of the 6th China Aeronautical Science and Technology Conference - Volume II",
address = "德国",
}