Knowledge Commons of Institute of Automation,CAS
Tacit Commitments Emergence in Multi-agent Reinforcement Learning | |
Liu BY(刘博寅)1,2![]() ![]() ![]() | |
2023 | |
会议名称 | International Conference on Neural Information Processing |
会议日期 | 2023-7 |
会议地点 | New Delhi, India |
摘要 | Tacit commitments have been widely seen as a crucial underpinning for real-world cooperation. Similarly, it could also be a key to multi-agent cooperation. This paper proposes a novel tacit commitment emergence multi-agent reinforcement learning (MARL) framework (TCEM). In MARL, we define commitment as the unique state that the agent will exhibit through its action. TCEM first equips each agent with a commitment inference module (CIM) to infer its neighbor's commitments. Then, TCEM proposes that commitments influence intrinsic motivation (CIR) to encourage agents to have casual influence on others' actions. Finally, commitment acceptance intrinsic (CAI) motivation is constructed to guide the agent in behaving considering neighbors' commitments. CIR and CAI calculate intrinsic reward using counterfactual reasoning deriving from causal inference. Empirical results show that our method can effectively improve learning performance and deliver better cooperation among agents, which helps our method show superior performance on the Google Research Football benchmark. |
收录类别 | EI |
七大方向——子方向分类 | 强化与进化学习 |
国重实验室规划方向分类 | 认知决策知识体系 |
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/173211/58541 |
专题 | 复杂系统认知与决策实验室_群体决策智能团队 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences 3.Alibaba Group, Hangzhou, China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Liu BY,Zhiqiang Pu,Junlong Gao,et al. Tacit Commitments Emergence in Multi-agent Reinforcement Learning[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 | ||
Tacit_Commitments_Em(932KB) | 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