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 2402.09456cs.LGcs.AIcs.GTstat.ML
收藏

未知博弈中无悔学习的乐观汤普森采样

Optimistic Thompson Sampling for No-Regret Learning in Unknown Games

The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院)

Yingru Li, Liangqi Liu, Wenqiang Pu, Hao Liang, Zhi-Quan Luo

AI总结:

本文针对未知博弈中的多玩家决策问题,提出基于汤普森采样的算法,利用对手动作与奖励结构将实验预算降低十倍以上,并给出对数级遗憾界,同时提出先乐观后无悔框架并在交通路由与雷达感知中验证其有效性。

摘要:

本文针对未知博弈中多玩家场景的复杂性展开研究,其核心挑战在于需要在通过老虎机反馈感知环境不确定性的同时进行策略决策。我们提出了基于汤普森采样(Thompson Sampling,TS)的算法,该算法能够利用对手动作信息和奖励结构,从而大幅减少实验预算——与传统方法相比实现了超过十倍的改进。值得注意的是,我们的算法表明,在给定特定奖励结构的情况下,遗憾界仅与总动作空间呈对数关系,显著缓解了多玩家带来的维度灾难。此外,我们揭示了“先乐观后无悔”(Optimism-then-NoRegret,OTN)框架,这是一种开创性的方法,能够将我们的进展与已有算法无缝结合,并在交通路由和雷达感知等实际场景中展示了其实用价值。

英文摘要:

This work tackles the complexities of multi-player scenarios in \emph{unknown games}, where the primary challenge lies in navigating the uncertainty of the environment through bandit feedback alongside strategic decision-making. We introduce Thompson Sampling (TS)-based algorithms that exploit the information of opponents' actions and reward structures, leading to a substantial reduction in experimental budgets -- achieving over tenfold improvements compared to conventional approaches. Notably, our algorithms demonstrate that, given specific reward structures, the regret bound depends logarithmically on the total action space, significantly alleviating the curse of multi-player. Furthermore, we unveil the \emph{Optimism-then-NoRegret} (OTN) framework, a pioneering methodology that seamlessly incorporates our advancements with established algorithms, showcasing its utility in practical scenarios such as traffic routing and radar sensing in the real world.

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。

↑