Multi-Environment POMDPs with Finite-Horizon Objectives
Artificial Intelligence
2026-05-11 v1
Abstract
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.
Cite
@article{arxiv.2605.07537,
title = {Multi-Environment POMDPs with Finite-Horizon Objectives},
author = {Léonard Brice and Filip Cano and Krishnendu Chatterjee and Thomas A. Henzinger and Stefanie Muroya},
journal= {arXiv preprint arXiv:2605.07537},
year = {2026}
}