arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.12736cs.LGcs.GTstat.ML
收藏

时变零和博弈中的无悔学习

No-Regret Learning in Time-Varying Zero-Sum Games

University of Southern California(南加利福尼亚大学);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室)

Mengxiao Zhang, Peng Zhao, Haipeng Luo, Zhi-Hua Zhou

摘要:

在固定的两人零和博弈中,从重复博弈中学习是博弈论和在线学习中的经典问题。我们考虑这个问题的一个变体,其中游戏收益矩阵随时间变化,可能是以对抗的方式。我们首先提出了三个性能指标来指导这个问题的算法设计:1)充分研究的个人遗憾,2)二元差距的扩展,和3)一个新的措施,称为动态纳什均衡遗憾,它量化了玩家的回报和极大极小博弈值之间的累积差异。接下来,我们开发了一个单一的无参数算法,同时享有所有这三个性能指标的有利保证。这些保证是适应不同的非平稳措施的回报矩阵,重要的是,恢复最好的已知结果时,回报矩阵是固定的。我们的算法是基于一个两层结构的元算法学习一组黑盒基学习满足一定的属性,随着几个新的成分专门设计的时变游戏设置。实验结果进一步验证了算法的有效性。

英文摘要:

Learning from repeated play in a fixed two-player zero-sum game is a classic problem in game theory and online learning. We consider a variant of this problem where the game payoff matrix changes over time, possibly in an adversarial manner. We first present three performance measures to guide the algorithmic design for this problem: 1) the well-studied individual regret, 2) an extension of duality gap, and 3) a new measure called dynamic Nash Equilibrium regret, which quantifies the cumulative difference between the player's payoff and the minimax game value. Next, we develop a single parameter-free algorithm that simultaneously enjoys favorable guarantees under all these three performance measures. These guarantees are adaptive to different non-stationarity measures of the payoff matrices and, importantly, recover the best known results when the payoff matrix is fixed. Our algorithm is based on a two-layer structure with a meta-algorithm learning over a group of black-box base-learners satisfying a certain property, along with several novel ingredients specifically designed for the time-varying game setting. Empirical results further validate the effectiveness of our algorithm.

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。

↑