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 2201.04266cs.GTcs.AIcs.CRcs.MAecon.TH
收藏

安全均衡

Safe Equilibrium

Ganzfried Research(甘茨弗里德研究机构)

Sam Ganzfried

AI总结:

本文提出安全均衡,以指定概率刻画对手理性、其余概率任意行动,证明其普遍存在且计算 PPAD-hard,并给出二人与 n 人博弈的精确及可扩展近似算法。

摘要:

标准的博弈论解概念 Nash 均衡假设所有参与者都理性行事。如果我们遵循某个 Nash 均衡,而对手是非理性的(或遵循来自另一个 Nash 均衡的策略),那么我们可能获得极低的收益。另一方面,maximin 策略假设所有对立智能体都在以最小化我们的收益为目标行动(即使这并不符合他们的最佳利益),并确保在最坏情况下获得尽可能高的收益,但会导致极其保守的行动。我们提出一种称为安全均衡的新解概念,它将对手建模为以指定概率理性行事,并以剩余概率可能任意行事。我们证明,安全均衡存在于所有策略式博弈中(对理性参数的所有可能取值均成立),并证明其计算是 PPAD-hard。我们给出了在 2 人和 n 人博弈中计算安全均衡的精确算法,以及可扩展的近似算法。

英文摘要:

The standard game-theoretic solution concept, Nash equilibrium, assumes that all players behave rationally. If we follow a Nash equilibrium and opponents are irrational (or follow strategies from a different Nash equilibrium), then we may obtain an extremely low payoff. On the other hand, a maximin strategy assumes that all opposing agents are playing to minimize our payoff (even if it is not in their best interest), and ensures the maximal possible worst-case payoff, but results in exceedingly conservative play. We propose a new solution concept called safe equilibrium that models opponents as behaving rationally with a specified probability and behaving potentially arbitrarily with the remaining probability. We prove that a safe equilibrium exists in all strategic-form games (for all possible values of the rationality parameters), and prove that its computation is PPAD-hard. We present exact algorithms for computing a safe equilibrium in both 2 and $n$-player games, as well as scalable approximation algorithms.

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。

↑