Knowledge Commons of Institute of Automation,CAS
Model-Free Reinforcement Learning for Fully Cooperative Multi-Agent Graphical Games | |
Zhang Qichao1,2; Zhao Dongbin1,2; F.L.Lewis | |
2018 | |
会议名称 | International Joint Conference on Neural Networks (IJCNN) |
会议日期 | July 8-13 |
会议地点 | Rio de Janeiro, Brazil |
摘要 | In this paper, the optimal coordinated control problem for the homogeneous multi-agent graphical games with completely unknown dynamics is investigated. The off-policy reinforcement learning is proposed to approach the solution of the Hamilton-Jacobi equation under the framework of centralized training and decentralized execution. The actor-critic structure is adopted to learn the optimal control policies. Note that the critic network is centralized using the information from all the agents, and the parameter sharing scheme is adopted for the single actor network during the training process. For the execution process, the centralized critic network is not required, and only the trained actor network is used for each agent to obtain the control input based on its individual observation. For the implementation purpose, the neural network approximators with the actor-critic structure are constructed to approach the optimal centralized value function and the optimal policies for the multiagent graphical games. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed algorithm. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26140 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
作者单位 | 1.Institute of Automation, CAS 2.University of Chinese Academy of Sciences, CAS |
推荐引用方式 GB/T 7714 | Zhang Qichao,Zhao Dongbin,F.L.Lewis. Model-Free Reinforcement Learning for Fully Cooperative Multi-Agent Graphical Games[C],2018. |
条目包含的文件 | 条目无相关文件。 |
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