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 2102.10104cs.GTcs.FLcs.LO
收藏

随机博弈中独立于竞技场的有限记忆确定性

Arena-Independent Finite-Memory Determinacy in Stochastic Games

Patricia Bouyer, Youssouf Oualhadj, Mickael Randour, Pierre Vandenhove

AI总结:

研究图上随机零和博弈中独立于竞技场的有限记忆(AIFM)确定性,证明纯AIFM策略存在子博弈完美策略,可将双人问题归约至单人Markov决策过程,并通过两个直观性质刻画AIFM策略充分性。

摘要:

我们研究图上的随机零和博弈,这是在随机环境中存在对抗性对手时对决策进行建模的常用工具。在此背景下,一个重要问题是策略复杂度:何种策略足以或必须用于实现最优博弈(例如随机化或记忆需求)?我们的贡献加深了对独立于竞技场的有限记忆(AIFM)确定性的理解,即研究需要记忆的目标,但记忆方式仅依赖于博弈图的有限参数。首先,我们证明纯AIFM策略足以实现最优博弈的目标,也允许纯AIFM子博弈完美策略。其次,我们证明可以将双人随机博弈中纯AIFM策略足以胜任的目标研究,归约到更简单的单人随机博弈(即Markov决策过程)研究。第三,我们通过目标的两个直观性质刻画了AIFM策略的充分性。这项工作将始于确定性博弈的研究路线扩展到了随机博弈。

英文摘要:

We study stochastic zero-sum games on graphs, which are prevalent tools to model decision-making in presence of an antagonistic opponent in a random environment. In this setting, an important question is the one of strategy complexity: what kinds of strategies are sufficient or required to play optimally (e.g., randomization or memory requirements)? Our contributions further the understanding of arena-independent finite-memory (AIFM) determinacy, i.e., the study of objectives for which memory is needed, but in a way that only depends on limited parameters of the game graphs. First, we show that objectives for which pure AIFM strategies suffice to play optimally also admit pure AIFM subgame perfect strategies. Second, we show that we can reduce the study of objectives for which pure AIFM strategies suffice in two-player stochastic games to the easier study of one-player stochastic games (i.e., Markov decision processes). Third, we characterize the sufficiency of AIFM strategies through two intuitive properties of objectives. This work extends a line of research started on deterministic games to stochastic ones.

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。

↑