A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning
文献类型：期刊论文
| 作者 | Fu, Qingxu1,2,3 ; Qiu, Tenghai1,2,3; Yi, Jianqiang1,2,3; Pu, Zhiqiang1,2,3; Ai, Xiaolin1,2,3; Yuan, Wanmai1,2,3
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2024-08-01 |
| 页码 | 15 |
| 关键词 | Task analysis Benchmark testing Psychology Multi-agent systems Reinforcement learning Entropy Analytical models Multiagent cooperation multiagent system neural network reinforcement learning (RL) |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2024.3423417 |
| 通讯作者 | Qiu, Tenghai(tenghai.qiu@ia.ac.cn) |
| 英文摘要 | State-of-the-art (SOTA) multiagent reinforcement algorithms distinguish themselves in many ways from their single-agent equivalences. However, most of them still totally inherit the single-agent exploration-exploitation strategy. Naively inheriting this strategy from single-agent algorithms causes potential collaboration failures, in which the agents blindly follow mainstream behaviors and reject taking minority responsibility. We name this problem the responsibility diffusion (RD) as it shares similarities with the same-name social psychology effect. In this work, we start by theoretically analyzing the cause of this RD problem, which can be traced back to the exploration-exploitation dilemma of multiagent systems (especially large-scale multiagent systems). We address this RD problem by proposing a policy resonance (PR) approach which modifies the collaborative exploration strategy of agents by refactoring the joint agent policy while keeping individual policies approximately invariant. Next, we show that SOTA algorithms can equip this approach to promote the collaborative performance of agents in complex cooperative tasks. Experiments are performed in multiple test benchmark tasks to illustrate the effectiveness of this approach. |
| WOS关键词 | ALGORITHMS |
| 资助项目 | Strategic Priority Research Program of Chinese Academy of Sciences[XDA27030204] ; National Natural Science Foundation of China[62322316] ; National Natural Science Foundation of China[62073323] ; Beijing Nova Program[20220484077] ; Beijing Nova Program[20230484435] ; National Key Research and Development Program of China[2018AAA0102404] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001283793300001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Strategic Priority Research Program of Chinese Academy of Sciences ; National Natural Science Foundation of China ; Beijing Nova Program ; National Key Research and Development Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59288]  |
| 专题 | 综合信息系统研究中心_飞行器智能技术 |
| 通讯作者 | Qiu, Tenghai |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.CETC Informat Sci Acad, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Fu, Qingxu,Qiu, Tenghai,Yi, Jianqiang,et al. A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2024:15. |
| APA | Fu, Qingxu,Qiu, Tenghai,Yi, Jianqiang,Pu, Zhiqiang,Ai, Xiaolin,&Yuan, Wanmai.(2024).A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15. |
| MLA | Fu, Qingxu,et al."A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2024):15. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。