CASIA OpenIR  > 深度强化学习团队
Value Iteration Algorithm for Optimal Consensus Control of Multi-agent Systems
Zhang Qichao1,2; Zhao Dongbin1,2
2018
Conference NameInternational Conference on Neural Information Processing(ICONIP)
Conference DateDec.14-16
Conference PlaceSiem Reap, Cambodia
Abstract

In this paper, we investigate the optimal consensus control problem for the multi-agent systems by utilizing the Heuristic Dynamic Programming (HDP) algorithm under the centralized learning and decentralized execution framework, which is a kind of value iteration algorithms in reinforcement learning. Different from independent learning framework, a centralized value function which is shared for all the agents is defined. To approach the Nash equilibrium, we prove the equivalence relationship between the Bellman optimality equation and the discrete-time Hamilton-Jacobi-Bellman (DTHJB) equation. For the implementation purpose, the actor-critic structure with NN approximators is proposed to approach the solution of DTHJB equation, where the critic network for all the agents is centralized using the global information, and each actor network for the corresponding agent is decentralized using the local information. Finally, the simulation results are provided, which demonstrates the effectiveness of the proposed HDP algorithm under the centralized learning and decentralized execution framework.

Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26141
Collection深度强化学习团队
Affiliation1.Institute of Automation, CAS
2.University of Chinese Academy of Sciences, CAS
Recommended Citation
GB/T 7714
Zhang Qichao,Zhao Dongbin. Value Iteration Algorithm for Optimal Consensus Control of Multi-agent Systems[C],2018.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang Qichao]'s Articles
[Zhao Dongbin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang Qichao]'s Articles
[Zhao Dongbin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang Qichao]'s Articles
[Zhao Dongbin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.