Academic Journal
Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives
| Title: | Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives |
|---|---|
| Authors: | Belly, Marius, Fijalkow, Nathanaël, Gimbert, Hugo, Horn, Florian, Pérez, Guillermo Alberto, Vandenhove, Pierre |
| Source: | AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25-March 4, 2025, Philadelphia, PA, USA Proceedings of the AAAI Conference on Artificial Intelligence |
| Publication Status: | Preprint |
| Publisher Information: | Association for the Advancement of Artificial Intelligence (AAAI), 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Computer. Automation, FOS: Computer and information sciences, Computer Science - Logic in Computer Science, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, FOS: Electrical engineering, electronic engineering, information engineering, Systems and Control (eess.SY), Electrical Engineering and Systems Science - Systems and Control, Logic in Computer Science (cs.LO) |
| Description: | Partially observable Markov decision processes (POMDPs) form a prominent model for uncertainty in sequential decision making. We are interested in constructing algorithms with theoretical guarantees to determine whether the agent has a strategy ensuring a given specification with probability 1. This well-studied problem is known to be undecidable already for very simple omega-regular objectives, because of the difficulty of reasoning on uncertain events. We introduce a revelation mechanism which restricts information loss by requiring that almost surely the agent has eventually full information of the current state. Our main technical results are to construct exact algorithms for two classes of POMDPs called weakly and strongly revealing. Importantly, the decidable cases reduce to the analysis of a finite belief-support Markov decision process. This yields a conceptually simple and exact algorithm for a large class of POMDPs. |
| Document Type: | Article Conference object |
| ISSN: | 2374-3468 2159-5399 |
| DOI: | 10.1609/aaai.v39i25.34845 |
| DOI: | 10.48550/arxiv.2412.12063 |
| Access URL: | http://arxiv.org/abs/2412.12063 https://repository.uantwerpen.be/docstore/d:irua:28676 https://hdl.handle.net/10067/2140840151162165141 |
| Rights: | CC BY SA |
| Accession Number: | edsair.doi.dedup.....c6820c36ef0f87a7f37e7c0dbf0b8013 |
| Database: | OpenAIRE |
| ISSN: | 23743468 21595399 |
|---|---|
| DOI: | 10.1609/aaai.v39i25.34845 |