arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.02663cs.GTcs.SYeess.SY
收藏

部分观测下多矩阵博弈的广义个体Q学习

Generalized Individual Q-learning for Polymatrix Games with Partial Observations

Ahmed Said Donmez, Muhammed O. Sayin

AI总结:

本文提出广义个体Q学习,融合信念与收益学习,在部分观测多矩阵博弈中实现更快收敛到分位数响应均衡,并统一了光滑虚拟博弈与个体Q学习。

摘要:

本文解决了非合作多智能体系统中有限观测的挑战,其中智能体只能部分获取其他智能体的动作。我们提出了广义个体Q学习动力学,该动力学结合了基于信念和基于收益的学习,适用于超过两个自利智能体的网络化互联。该方法尽可能利用对对手动作的访问,可证明地在多智能体零和博弈和势多矩阵博弈中实现更快(有保证)的收敛到分位数响应均衡。值得注意的是,在完全访问和无法访问对手动作的情况下,该动力学分别退化为已被充分研究的光滑虚拟博弈和个体Q学习。我们进一步通过数值仿真量化了由于观测对手动作而带来的收敛速度提升。

英文摘要:

This paper addresses the challenge of limited observations in non-cooperative multi-agent systems where agents can have partial access to other agents' actions. We present the generalized individual Q-learning dynamics that combine belief-based and payoff-based learning for the networked interconnections of more than two self-interested agents. This approach leverages access to opponents' actions whenever possible, demonstrably achieving a faster (guaranteed) convergence to quantal response equilibrium in multi-agent zero-sum and potential polymatrix games. Notably, the dynamics reduce to the well-studied smoothed fictitious play and individual Q-learning under full and no access to opponent actions, respectively. We further quantify the improvement in convergence rate due to observing opponents' actions through numerical simulations.

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。

↑