arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00603cs.GTcs.AIcs.LGcs.MA
收藏

可拓形式相关均衡的无悔学习动力学

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

Politecnico di Milano(米兰理工大学);Carnegie Mellon University(卡内基梅隆大学)

Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti

摘要:

在规范型博弈中,简单的、解耦的无悔动力学收敛到相关均衡的存在是多智能体系统理论中的一个著名结果。具体来说,20多年前就已经知道,当所有参与者在重复的正态形式博弈中寻求最小化他们的内部遗憾时,经验的博弈频率收敛到正态形式相关均衡。可拓形式(也就是树形)博弈通过对连续和同时移动以及私有信息进行建模来推广正规形式博弈。由于博弈中的序列性质和部分信息的存在,广义形式的相关性与正规形式的相关性有显着不同的性质,其中许多仍然是开放的研究方向。扩展形式相关均衡(EFCE)是规范形式相关均衡的自然扩展形式对应。然而,目前尚不清楚EFCE是否是由于解偶联剂动力学而出现的。在本文中,我们给出了第一个非耦合的无悔动力学收敛到集的EFCE在$n$ -播放器一般和扩展形式的游戏,完美的回忆。首先,我们引入了一个概念的触发遗憾的扩展形式的游戏,扩展了正常形式的游戏中的内部遗憾。当每个玩家都有低触发后悔时,经验的游戏频率接近EFCE。然后,我们给出了一个有效的无触发后悔算法。该算法将触发后悔问题分解为局中人在每个决策点的局部子问题,并由每个决策点的局部解构造局中人的全局策略。

英文摘要:

The existence of simple, uncoupled no-regret dynamics that converge to correlated equilibria in normal-form games is a celebrated result in the theory of multi-agent systems. Specifically, it has been known for more than 20 years that when all players seek to minimize their internal regret in a repeated normal-form game, the empirical frequency of play converges to a normal-form correlated equilibrium. Extensive-form (that is, tree-form) games generalize normal-form games by modeling both sequential and simultaneous moves, as well as private information. Because of the sequential nature and presence of partial information in the game, extensive-form correlation has significantly different properties than the normal-form counterpart, many of which are still open research directions. Extensive-form correlated equilibrium (EFCE) has been proposed as the natural extensive-form counterpart to normal-form correlated equilibrium. However, it was currently unknown whether EFCE emerges as the result of uncoupled agent dynamics. In this paper, we give the first uncoupled no-regret dynamics that converge to the set of EFCEs in $n$-player general-sum extensive-form games with perfect recall. First, we introduce a notion of trigger regret in extensive-form games, which extends that of internal regret in normal-form games. When each player has low trigger regret, the empirical frequency of play is close to an EFCE. Then, we give an efficient no-trigger-regret algorithm. Our algorithm decomposes trigger regret into local subproblems at each decision point for the player, and constructs a global strategy of the player from the local solutions at each decision point.

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。

↑