arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.06327cs.GTcs.LG
收藏

情境博弈:带边信息的多智能体学习

Contextual Games: Multi-Agent Learning with Side Information

ETH Zürich(苏黎世联邦理工学院)

Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause, Maryam Kamgarpour

摘要:

我们制定了新的类上下文游戏,一种类型的重复游戏驱动的上下文信息在每一轮。通过基于核的规律性假设,我们模拟不同的上下文和游戏结果之间的相关性,并提出了一种新的在线(Meta)算法,利用这种相关性,以尽量减少个别球员的上下文遗憾。我们定义了这类新游戏的上下文粗相关均衡(c-CCE)和最佳上下文福利的博弈论概念,并表明每当玩家的上下文遗憾消失时,c-CCE和最佳福利都可以接近。最后,我们经验验证我们的结果在交通路由实验中,我们的算法导致更好的性能和更高的福利相比,基线不利用可用的上下文信息或相关性存在于游戏中。

英文摘要:

We formulate the novel class of contextual games, a type of repeated games driven by contextual information at each round. By means of kernel-based regularity assumptions, we model the correlation between different contexts and game outcomes and propose a novel online (meta) algorithm that exploits such correlations to minimize the contextual regret of individual players. We define game-theoretic notions of contextual Coarse Correlated Equilibria (c-CCE) and optimal contextual welfare for this new class of games and show that c-CCEs and optimal welfare can be approached whenever players' contextual regrets vanish. Finally, we empirically validate our results in a traffic routing experiment, where our algorithm leads to better performance and higher welfare compared to baselines that do not exploit the available contextual information or the correlations present in the game.

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。

↑