Consensus Learning for Cooperative Multi-Agent Reinforcement Learning | |
Zhiwei Xu1,2; Bin Zhang1,2; Dapeng Li1,2; Zeren Zhang1,2; Guangchong Zhou1,2; Hao Chen1,2; Guoliang Fan1,2 | |
2023 | |
会议日期 | February 7-14, 2023 |
会议地点 | Washington, DC, USA |
DOI | 10.1609/AAAI.V37I10.26385 |
页码 | 11726–11734 |
英文摘要 | Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During the centralized training, agents can be guided by the same signals, such as the global state. However, agents lack the shared signal and choose actions given local observations during execution. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this study. Although based on local observations, different agents can infer the same consensus in discrete spaces without communication. We feed the inferred one-hot consensus to the network of agents as an explicit input in a decentralized way, thereby fostering their cooperative spirit. With minor model modifications, our suggested framework can be extended to a variety of multi-agent reinforcement learning algorithms. Moreover, we carry out these variants on some fully cooperative tasks and get convincing results. |
语种 | 英语 |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/56530] ![]() |
专题 | 融合创新中心_决策指挥与体系智能 |
通讯作者 | Guoliang Fan |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhiwei Xu,Bin Zhang,Dapeng Li,et al. Consensus Learning for Cooperative Multi-Agent Reinforcement Learning[C]. 见:. Washington, DC, USA. February 7-14, 2023. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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