Ensuring logic in the fog: sound POMDP synthesis with LTL objectives
File(s)
Accepted version
Author(s)
Can, Zhou
Gao, Yulong
Pian, Yu
Type
Conference Paper
Abstract
Synthesising autonomous agents that can navigate uncertain environments while adhering to complex temporal constraints remains a fundamental challenge. While Linear Temporal Logic (LTL) provides a rigorous language for specifying such tasks, the inherent undecidability of qualitatively verifying LTL satisfaction in partially observable Markov decision processes renders quantitative synthesis difficult, especially when designing reliable reward signals for approximate solvers. In this paper, we bridge this gap with a novel, sound reward-shaping mechanism that dynamically generates belief-dependent rewards grounded in certified LTL satisfaction. By integrating this mechanism into an enhanced Monte Carlo Planning framework, we empower agents to navigate the ‘fog’ of partial observability with a search process focused on maximising verifiable success. Our experiments demonstrate that this approach not only thrives in scenarios where existing solvers fail but also maintains effectiveness and scalability across diverse benchmark domains.
Date Acceptance
2026-04-29
Citation
Proceedings of the 35th International Joint Conference on Artificial Intelligence
Publisher
IJCAI
Journal / Book Title
Proceedings of the 35th International Joint Conference on Artificial Intelligence
Copyright Statement
Subject to copyright. This paper is embargoed until publication. Once published the author’s accepted manuscript will be made available under a CC-BY License in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy).
License URL
Source
35th International Joint Conference on Artificial Intelligence
Publication Status
Accepted
Start Date
2026-08-15
Finish Date
2021-08-21
Coverage Spatial
Bremen, Germany