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 1606.08718cs.GT
收藏

从批量数据中学习一般和马尔可夫博弈的纳什均衡

Learning Nash Equilibrium for General-Sum Markov Games from Batch Data

Julien Pérolat, Florian Strub, Bilal Piot, Olivier Pietquin

摘要:

研究了$γ$ -折扣多人一般和马尔可夫博弈(MG)的纳什均衡学习问题。这个模型的一个关键组成部分是玩家可以合作或分开来增加他们的奖励。建立一个人工的球员一般和MG意味着学习更复杂的策略,这是不可能通过使用技术开发的两个球员零和MG。本文引入了一种新的多人博弈中的$ε$ -纳什均衡的定义,它把握了多人博弈中策略的性质。我们证明了最小化两个Bellman样残差的范数意味着收敛到这样的$ε$ -纳什均衡。然后,我们表明,最大限度地减少这些贝尔曼样残差的$L_p$范数的经验估计允许学习的一般和游戏内的批处理设置。最后,我们介绍了一个名为NashNetwork的神经网络架构,成功地学习了一个通用的多人一般和回合制MG的纳什均衡。

英文摘要:

This paper addresses the problem of learning a Nash equilibrium in $γ$-discounted multiplayer general-sum Markov Games (MG). A key component of this model is the possibility for the players to either collaborate or team apart to increase their rewards. Building an artificial player for general-sum MGs implies to learn more complex strategies which are impossible to obtain by using techniques developed for two-player zero-sum MGs. In this paper, we introduce a new definition of $ε$-Nash equilibrium in MGs which grasps the strategy's quality for multiplayer games. We prove that minimizing the norm of two Bellman-like residuals implies the convergence to such an $ε$-Nash equilibrium. Then, we show that minimizing an empirical estimate of the $L_p$ norm of these Bellman-like residuals allows learning for general-sum games within the batch setting. Finally, we introduce a neural network architecture named NashNetwork that successfully learns a Nash equilibrium in a generic multiplayer general-sum turn-based MG.

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。

↑