多环境马尔可夫决策过程
Multiple-Environment Markov Decision Processes
AI总结:
本文提出多环境马尔可夫决策过程,旨在设计一个控制器以保证在未知环境中性能,解决了部分可观测MDP中不可判定的问题。
摘要:
我们引入了多环境马尔可夫决策过程(MEMDPs),即具有概率转移函数集合的MDP。在MEMDP中,目标是合成一个控制器,以保证在所有环境中都能获得保证的性能,即使环境事先未知。虽然MEMDP可以被视为部分可观测MDP的特殊类,但我们证明了几个在部分可观测MDP中不可判定的验证问题,在MEMDP中是可判定的,有时甚至有高效的解法。
英文摘要:
We introduce Multi-Environment Markov Decision Processes (MEMDPs) which are MDPs with a set of probabilistic transition functions. The goal in a MEMDP is to synthesize a single controller with guaranteed performances against all environments even though the environment is unknown a priori. While MEMDPs can be seen as a special class of partially observable MDPs, we show that several verification problems that are undecidable for partially observable MDPs, are decidable for MEMDPs and sometimes have even efficient solutions.
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。