Strategy Synthesis in POMDPs via Game-Based AbstractionsDownload PDF

Leonore Winterer, Sebastian Junges, Ralf Wimmer, Nils Jansen, Ufuk Topcu, Joost-Pieter Katoen, Bernd Becker

28 May 2019 (modified: 05 May 2023)RSS 2019Readers: Everyone
Keywords: Planning, POMDPs, MDPs, Partial Observability, Formal Verification, AI
TL;DR: This paper provides a game-based abstraction scheme to compute provably sound policies for POMDPs.
Abstract: Partially observable Markov decision processes (POMDPs) are a natural model for scenarios where one has to deal with incomplete knowledge and random events. Applications include, but are not limited to, robotics and motion planning. However, many relevant properties of POMDPs are either undecidable or very expensive to compute in terms of both runtime and memory consumption. In our work, we develop a game-based abstraction method that is able to deliver safe bounds and tight approximations for important sub-classes of such properties. We discuss the theoretical implications and showcase the applicability of our results on a broad spectrum of benchmarks.
0 Replies

Loading