arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1102.4121cs.LOcs.CC
收藏

马尔可夫决策过程的同步目标

Synchronizing Objectives for Markov Decision Processes

Laurent Doyen, Thierry Massart, Mahsa Shirmohammadi

摘要:

我们介绍了马尔可夫决策过程(MDP)的同步目标。直觉上,同步目标要求最终在每一步都有一个状态,它几乎集中了所有的概率质量。特别是,它意味着概率系统在长期内表现得像一个确定性系统:最终,MDP的当前状态几乎可以确定。我们研究的问题,决定存在一个战略,以执行同步目标的MDPs。我们发现,这个问题是可判定的一般策略,以及盲目的策略,玩家不能观察到的MDP的当前状态。我们还表明,纯策略是足够的,但内存可能是必要的。

英文摘要:

We introduce synchronizing objectives for Markov decision processes (MDP). Intuitively, a synchronizing objective requires that eventually, at every step there is a state which concentrates almost all the probability mass. In particular, it implies that the probabilistic system behaves in the long run like a deterministic system: eventually, the current state of the MDP can be identified with almost certainty. We study the problem of deciding the existence of a strategy to enforce a synchronizing objective in MDPs. We show that the problem is decidable for general strategies, as well as for blind strategies where the player cannot observe the current state of the MDP. We also show that pure strategies are sufficient, but memory may be necessary.

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。

↑