首页|Robust cooperative multi-agent reinforcement learning via multi-view message certification

Robust cooperative multi-agent reinforcement learning via multi-view message certification

扫码查看
原文链接
  • 万方数据
  • 维普
Many multi-agent scenarios require message sharing among agents to promote coordination,hastening the robustness of multi-agent communication when policies are deployed in a message perturbation environment.Major relevant studies tackle this issue under specific assumptions,like a limited number of message channels would sustain perturbations,limiting the efficiency in complex scenarios.In this paper,we take a further step in addressing this issue by learning a robust cooperative multi-agent reinforcement learning via multi-view message certification,dubbed CroMAC.Agents trained under CroMAC can obtain guaranteed lower bounds on state-action values to identify and choose the optimal action under a worst-case deviation when the received messages are perturbed.Concretely,we first model multi-agent communication as a multi-view problem,where every message stands for a view of the state.Then we extract a certificated joint message representation by a multi-view variational autoencoder(MVAE)that uses a product-of-experts inference network.For the optimization phase,we do perturbations in the latent space of the state for a certificate guarantee.Then the learned joint message representation is used to approximate the certificated state representation during training.Extensive experiments in several cooperative multi-agent benchmarks validate the effectiveness of the proposed CroMAC.

multi-agent reinforcement learningrobust communicationadversarial trainingmulti-view learningmessage certification

Lei YUAN、Tao JIANG、Lihe LI、Feng CHEN、Zongzhang ZHANG、Yang YU

展开 >

National Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210023,China

Polixir Technologies,Nanjing 211106,China

国家重点研发计划国家自然科学基金国家自然科学基金国家自然科学基金江苏省自然科学基金Program B for Outstanding PhD Candidate of Nanjing University

2020AAA0107200619210066187611962276126BK20221442

2024

10.1007/s11432-023-3853-y

中国科学:信息科学(英文版)
中国科学院

中国科学:信息科学(英文版)

CSTPCDEI
影响因子：0.715
ISSN：1674-733X
年,卷(期)：2024.67(4)
  • 93