arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.06334eess.SYcs.AIcs.ITcs.SYmath.ITmath.OCnlin.AO
收藏

多智能体系统的完全去中心化策略:信息论方法

Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach

University of California, Berkeley(加州大学伯克利分校)

Roel Dobbe, David Fridovich-Keil, Claire Tomlin

AI总结:

本文提出基于信息论的框架,用于多智能体系统中无通信条件下的去中心化策略设计,通过率失真理论分析策略重建最优解的能力,并扩展至确定通信节点以提升个体策略性能。

摘要:

在多智能体系统中学习合作策略常受部分可观测性和协调不足的挑战。在某些情况下,问题结构允许通过有限通信实现分布式解决方案。本文考虑无通信可用的场景,学习所有智能体的局部策略以集体模拟集中多智能体静态优化问题的解。我们的主要贡献是基于率失真理论的信息论框架,该框架有助于分析所得到的完全去中心化策略重建最优解的能力。此外,该框架提供了一种自然扩展,以确定智能体应与哪些节点通信以提高其个体策略的性能。

英文摘要:

Learning cooperative policies for multi-agent systems is often challenged by partial observability and a lack of coordination. In some settings, the structure of a problem allows a distributed solution with limited communication. Here, we consider a scenario where no communication is available, and instead we learn local policies for all agents that collectively mimic the solution to a centralized multi-agent static optimization problem. Our main contribution is an information theoretic framework based on rate distortion theory which facilitates analysis of how well the resulting fully decentralized policies are able to reconstruct the optimal solution. Moreover, this framework provides a natural extension that addresses which nodes an agent should communicate with to improve the performance of its individual policy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑