Enregistré dans:
Détails bibliographiques
Auteurs principaux: Brice, Léonard, Cano, Filip, Chatterjee, Krishnendu, Henzinger, Thomas A., Muroya, Stefanie
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.07537
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914543496593408
author Brice, Léonard
Cano, Filip
Chatterjee, Krishnendu
Henzinger, Thomas A.
Muroya, Stefanie
author_facet Brice, Léonard
Cano, Filip
Chatterjee, Krishnendu
Henzinger, Thomas A.
Muroya, Stefanie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07537
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Environment POMDPs with Finite-Horizon Objectives
Brice, Léonard
Cano, Filip
Chatterjee, Krishnendu
Henzinger, Thomas A.
Muroya, Stefanie
Artificial Intelligence
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.
title Multi-Environment POMDPs with Finite-Horizon Objectives
topic Artificial Intelligence
url https://arxiv.org/abs/2605.07537