From Coalgebraic Determinization to Belief Construction for Partial Observability
Mayuko Kori, Kazuki Watanabe

TL;DR
This paper introduces a coalgebraic framework for belief construction in partially observable systems, unifying semantics and providing new equivalence results for POMDPs and weighted transition systems.
Contribution
It develops a coalgebraic approach to belief construction, generalizing existing methods and establishing semantic equivalences for partially observable systems.
Findings
Semantics of partially observable systems matches that of belief coalgebras.
Standard equivalence between POMDPs and belief MDPs is recovered.
New equivalence result for weighted transition systems with semimodule monad.
Abstract
The belief construction is a fundamental technique for transforming partially observable systems to fully observable ones while preserving the relevant semantics. It plays a central role in the analysis of partially observable systems, in particular partially observable Markov decision processes (POMDPs), which is a central model in artificial intelligence and formal verification. In this paper, we develop a coalgebraic framework for the belief construction. To handle observations categorically, we lift a monad to slice categories and introduce a belief decomposition that reorganizes states according to their observations. This allows us to introduce a coalgebraic generalization of the belief construction, obtained by combining the belief decomposition with the coalgebraic determinization of Silva, Bonchi, Bonsangue, and Rutten. In this framework, we show that the semantics of a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
