arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.20133cs.GTcs.LO
收藏

不完全信息的正则博弈并非那么正则

Regular Games with Imperfect Information Are Not That Regular

Laurent Doyen, Thomas Soullard

AI总结:

研究不完全信息双人博弈中随机化策略的合成问题,提出正则博弈概念,证明在更一般模型中纯策略归约不适用,但在Buechi目标下随机化策略合成可判定。

摘要:

我们考虑具有不完全信息的双人博弈,以及为其中一方合成随机化策略,以确保无论另一方的策略如何,目标都能几乎必然(即概率为1)满足。不完全信息通过描述第一方无法区分的历史对的一个不可区分关系来建模,这是传统部分观测模型的推广。如果博弈允许一个其核与不可区分关系交换的正则函数,则该博弈是正则的。通过适用于所有目标的通用归约,在正则博弈中可以合成确保所有可能结果满足目标的纯策略。尽管纯策略的解在传统部分观测模型(始终是正则的)中可扩展至随机化策略,我们证明在更一般的模型中不存在类似归约。尽管如此,我们证明在具有Buechi目标的正则博弈中,对于确保结果几乎必然满足目标的随机化策略,合成问题是可判定的。

英文摘要:

We consider two-player games with imperfect information and the synthesis of a randomized strategy for one player that ensures the objective is satisfied almost-surely (i.e., with probability 1), regardless of the strategy of the other player. Imperfect information is modeled by an indistinguishability relation describing the pairs of histories that the first player cannot distinguish, a generalization of the traditional model with partial observations. The game is regular if it admits a regular function whose kernel commutes with the indistinguishability relation. The synthesis of pure strategies that ensure all possible outcomes satisfy the objective is possible in regular games, by a generic reduction that holds for all objectives. While the solution for pure strategies extends to randomized strategies in the traditional model with partial observations (which is always regular), we show that a similar reduction does not exist in the more general model. Despite that, we show that in regular games with Buechi objectives the synthesis problem is decidable for randomized strategies that ensure the outcome satisfies the objective almost-surely.

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。

↑