arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.05065cs.LO
收藏

可数MDP中奇偶性目标的策略复杂性

Strategy Complexity of Parity Objectives in Countable MDPs

Stefan Kiefer, Richard Mayr, Mahsa Shirmohammadi, Patrick Totzke

摘要:

我们研究可数无限MDP奇偶目标。与有限MDP不同,最优策略不需要存在,如果存在,可能需要无限内存。我们提供了一个完整的图片的确切的策略复杂性的$\varepsilon$ -最优策略(和最优策略,如果它们存在)的所有子类的奇偶校验目标的Mostowski层次结构。根据颜色的数量、MDP的分支度以及是否考虑$\varepsilon$ -最优或最优策略,MD策略、马尔可夫策略或1位马尔可夫策略都是必要且充分的。特别地,1比特马尔可夫策略对于$\varepsilon$ -最优(分别为:最优)策略。

英文摘要:

We study countably infinite MDPs with parity objectives. Unlike in finite MDPs, optimal strategies need not exist, and may require infinite memory if they do. We provide a complete picture of the exact strategy complexity of $\varepsilon$-optimal strategies (and optimal strategies, where they exist) for all subclasses of parity objectives in the Mostowski hierarchy. Either MD-strategies, Markov strategies, or 1-bit Markov strategies are necessary and sufficient, depending on the number of colors, the branching degree of the MDP, and whether one considers $\varepsilon$-optimal or optimal strategies. In particular, 1-bit Markov strategies are necessary and sufficient for $\varepsilon$-optimal (resp. optimal) strategies for general parity objectives.

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。

↑