arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09364cs.GTcs.AImath.OC
收藏

与无悔的球员比赛

Playing against no-regret players

ANITI(ANITI(人工智能与自然智能研究所));Toulouse School of Economics(图卢兹经济学院);UT Capitole(图卢兹第一大学)

Maurizio D 'Andrea

摘要:

在越来越不同的环境中,人类玩家必须与人工玩家互动,人工玩家根据决策算法做出决策。人类玩家应该如何对抗这些算法以最大化他的效用?如果他面对一个或多个人造球员,会有什么变化吗?本文的主要目的就是回答这两个问题。考虑在范式中随着时间的推移重复的n个玩家游戏,我们称人类玩家为优化器,而(n - 1)个人工玩家为学习器。我们假设学习者玩无遗憾算法,一类广泛应用于在线学习和决策的算法。在这些博弈中,我们考虑Stackelberg均衡的概念。在最近的一篇论文中,Deng,Schneider和Sivan证明了在一个2人游戏中,优化器总是可以保证每轮的预期累积效用至少为Stackelberg值。在我们的第一个结果中,我们用反例表明,如果优化器必须面对多个玩家,则该结果不再为真。因此,我们推广了Stackelberg均衡的定义,引入了相关Stackelberg均衡的概念。最后,在主要结果中,我们证明了优化器至少可以保证每轮的相关Stackelberg值。此外,使用一个版本的强大数定律,我们表明,我们的结果也几乎肯定是真的优化工具,而不是优化的预期效用。

英文摘要:

In increasingly different contexts, it happens that a human player has to interact with artificial players who make decisions following decision-making algorithms. How should the human player play against these algorithms to maximize his utility? Does anything change if he faces one or more artificial players? The main goal of the paper is to answer these two questions. Consider n-player games in normal form repeated over time, where we call the human player optimizer, and the (n -- 1) artificial players, learners. We assume that learners play no-regret algorithms, a class of algorithms widely used in online learning and decision-making. In these games, we consider the concept of Stackelberg equilibrium. In a recent paper, Deng, Schneider, and Sivan have shown that in a 2-player game the optimizer can always guarantee an expected cumulative utility of at least the Stackelberg value per round. In our first result, we show, with counterexamples, that this result is no longer true if the optimizer has to face more than one player. Therefore, we generalize the definition of Stackelberg equilibrium introducing the concept of correlated Stackelberg equilibrium. Finally, in the main result, we prove that the optimizer can guarantee at least the correlated Stackelberg value per round. Moreover, using a version of the strong law of large numbers, we show that our result is also true almost surely for the optimizer utility instead of the optimizer's expected utility.

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。

↑