Knowledge Commons of Institute of Automation,CAS
Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL | |
Zhiwei Xu1,2; Bin Zhang1,2; Dapeng Li1,2; Guangchong Zhou1,2; Zeren Zhang1,2; Guoliang Fan1,2 | |
2023 | |
会议名称 | Advances in Neural Information Processing Systems |
会议日期 | December 10-16, 2023 |
会议地点 | New Orleans, LA, USA |
摘要 | Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise. Each agent consists of an ego policy for action selection and an alter ego value function to solve the credit assignment problem. The value function factorization can ignore the IGM assumption by utilizing an explicit search procedure. On the basis of the above, we also suggest a novel anti-ego exploration mechanism to avoid the algorithm becoming stuck in a local optimum. As the first fully IGM-free value decomposition method, our proposed framework achieves desirable performance in various cooperative tasks. |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 多智能体系统 |
国重实验室规划方向分类 | 多智能体决策 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56538 |
专题 | 复杂系统认知与决策实验室_决策指挥与体系智能 |
通讯作者 | Guoliang Fan |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhiwei Xu,Bin Zhang,Dapeng Li,et al. Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Dual Self-Awareness (8700KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论