arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.07537cs.AI
收藏

多环境POMDPs与有限时间目标

Multi-Environment POMDPs with Finite-Horizon Objectives

Institute of Science and Technology Austria(奥地利科学与技术研究所)

Léonard Brice, Filip Cano, Krishnendu Chatterjee, Thomas A. Henzinger, Stefanie Muroya

AI总结:

本文研究多环境POMDPs在有限时间目标下的最优值与策略计算,证明该问题在POMDPs中为PSPACE完全问题,并提出有效算法在经典基准上表现优异。

摘要:

部分可观测马尔可夫决策过程(POMDPs)是agent与随机环境交互并仅获取当前状态部分信息的系统。在多环境POMDP(MEPOMDP)中,初始状态未知且被敌手选择。本文聚焦于计算MEPOMDPs在有限时间目标下的最优值和策略。该问题在POMDPs中已知为PSPACE完全问题。我们的主要结果如下:(1)我们证明在更一般的MEPOMDP设定下该问题同样为PSPACE完全问题;(2)我们提出一种实用算法并在经典基准上进行评估,显著优于之前已知的唯一算法。

英文摘要:

Partially Observable Markov Decision Processes (POMDPs) are systems in which one agent interacts with a stochastic environment, and receives only partial information about the current state. In a multi-environment POMDP (MEPOMDP), the initial state is unknown, and assumed to be adversarially chosen. In this work we focus on computing the optimal value and policy in MEPOMDPs with finite-horizon objectives. That problem is known to be PSPACE-complete in POMDPs. Our main results are as follows: (1) we establish that it is also PSPACE-complete in the more general setting of MEPOMDPs; (2) we present a practical algorithm and evaluate it on classical benchmarks, significantly outperforming the only previously known algorithm.

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。

↑