Fuzzy Feedback Multiagent Reinforcement Learning for Adversarial Dynamic Multiteam Competitions
文献类型：期刊论文
| 作者 | Fu, Qingxu1,2,3 ; Pu, Zhiqiang1,2,3; Pan, Yi1,2,3; Qiu, Tenghai1,2,3; Yi, Jianqiang1,2,3
|
| 刊名 | IEEE TRANSACTIONS ON FUZZY SYSTEMS
 |
| 出版日期 | 2024-05-01 |
| 卷号 | 32期号:5页码:2811-2824 |
| 关键词 | Bayesian optimization (BayesOpt) fuzzy feedback control multiagent systems multiteam competition reinforcement learning (RL) |
| ISSN号 | 1063-6706 |
| DOI | 10.1109/TFUZZ.2024.3363053 |
| 通讯作者 | Fu, Qingxu(fuqingxu2019@ia.ac.cn) |
| 英文摘要 | A large proportion of recent studies on cooperative multiagent reinforcement learning (MARL) focus on the policy-learning process in scenarios with stationary opponents (or without opponents). This article, instead, investigates a different challenge of achieving team superiority in dynamic competitions among competitors that evolve dynamically with MARL. We aim to enhance the competitiveness of such MARL learners by enabling them to adjust their own learning settings dynamically, so as to take quick counter measures against the policy shift of competitor learners, or to learn faster to suppress the opponents. We propose a competitive automultiagent learner with fuzzy feedback (CALF) with two essential highlights: 1) CALF establishes feedback controllers to achieve real-time adjustments based on fuzzy logic, using human-readable fuzzy rules to provide significant explainability and flexibility; 2) CALF integrates Bayesian optimization to search and optimize the feedback fuzzy logic rules automatically. CALF can be used to apply real-time adjustments for MARL hyperparameters and intrinsic rewards. We also give solid empirical results to show that CALF significantly promotes team competitiveness in adversarial competitions, spanning from small-scale tasks involving two teams to large-scale tasks involving three teams and hundreds of agents. Furthermore, CALF exhibits superior competitiveness when engaging in competition with established competitors, such as Qmix, Qtran, and Qplex, in dynamic competitive environments. Moreover, the experiments also demonstrate that the integration of the fuzzy logic with Bayesian optimization offers considerable transferability and explainability, enabling a CALF-implemented learner optimized from one scenario to be transferred to other distinct scenarios. |
| WOS关键词 | LEVEL |
| 资助项目 | Strategic Priority Research Program of Chinese Academy of Sciences |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001214545400018 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Strategic Priority Research Program of Chinese Academy of Sciences |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59036]  |
| 专题 | 综合信息系统研究中心_飞行器智能技术 |
| 通讯作者 | Fu, Qingxu |
| 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,Pu, Zhiqiang,Pan, Yi,et al. Fuzzy Feedback Multiagent Reinforcement Learning for Adversarial Dynamic Multiteam Competitions[J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS,2024,32(5):2811-2824. |
| APA | Fu, Qingxu,Pu, Zhiqiang,Pan, Yi,Qiu, Tenghai,&Yi, Jianqiang.(2024).Fuzzy Feedback Multiagent Reinforcement Learning for Adversarial Dynamic Multiteam Competitions.IEEE TRANSACTIONS ON FUZZY SYSTEMS,32(5),2811-2824. |
| MLA | Fu, Qingxu,et al."Fuzzy Feedback Multiagent Reinforcement Learning for Adversarial Dynamic Multiteam Competitions".IEEE TRANSACTIONS ON FUZZY SYSTEMS 32.5(2024):2811-2824. |
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。