Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives

• URL: http://arxiv.org/abs/2412.12063v1
• Date: Mon, 16 Dec 2024 18:37:06 GMT
• Title: Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives
• Authors: Marius Belly, Nathanaël Fijalkow, Hugo Gimbert, Florian Horn, Guillermo A. Pérez, Pierre Vandenhove,
• Abstract summary: Partially observable Markov decision processes (POMDPs) form a prominent model for uncertainty in sequential decision making. We introduce a revelation mechanism which restricts information loss by requiring that almost surely the agent has eventually full information of the current state. This yields a conceptually simple and exact algorithm for a large class of POMDPs.
• Score: 5.696882834567791
• License:
• Abstract: 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.

Related papers

• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making. We present a process-based benchmark MR-Ben that demands a meta-reasoning skill. Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives [16.101435842520473]
  This paper studies the challenging yet important problem in POMDPs known as the (indefinite-horizon) Maximal Reachability Probability Problem. Inspired by the success of point-based methods developed for discounted problems, we study their extensions to MRPP. We present a novel algorithm that leverages the strengths of these techniques for efficient exploration of the belief space.
  arXiv  Detail & Related papers  (2024-06-05T02:33:50Z)
• Learning Algorithms for Verification of Markov Decision Processes [20.5951492453299]
  We present a general framework for applying learning algorithms to the verification of Markov decision processes (MDPs) The presented framework focuses on probabilistic reachability, which is a core problem in verification.
  arXiv  Detail & Related papers  (2024-03-14T08:54:19Z)
• Online POMDP Planning with Anytime Deterministic Guarantees [11.157761902108692]
  Planning under uncertainty can be mathematically formalized using partially observable Markov decision processes (POMDPs) Finding an optimal plan for POMDPs can be computationally expensive and is feasible only for small tasks. We derive a deterministic relationship between a simplified solution that is easier to obtain and the theoretically optimal one.
  arXiv  Detail & Related papers  (2023-10-03T04:40:38Z)
• End-to-End Policy Gradient Method for POMDPs and Explainable Agents [2.1700203922407493]
  We propose an RL algorithm that estimates the hidden states by end-to-end training, and visualize the estimation as a state-transition graph. Experimental results demonstrated that the proposed algorithm can solve simple POMDP problems and that the visualization makes the agent's behavior interpretable to humans.
  arXiv  Detail & Related papers  (2023-04-19T15:45:52Z)
• Optimistic MLE -- A Generic Model-based Algorithm for Partially Observable Sequential Decision Making [48.87943416098096]
  This paper introduces a simple efficient learning algorithms for general sequential decision making. We prove that OMLE learns near-optimal policies of an enormously rich class of sequential decision making problems.
  arXiv  Detail & Related papers  (2022-09-29T17:56:25Z)
• Regret Analysis in Deterministic Reinforcement Learning [78.31410227443102]
  We study the problem of regret, which is central to the analysis and design of optimal learning algorithms. We present logarithmic problem-specific regret lower bounds that explicitly depend on the system parameter.
  arXiv  Detail & Related papers  (2021-06-27T23:41:57Z)
• Identification of Unexpected Decisions in Partially Observable Monte-Carlo Planning: a Rule-Based Approach [78.05638156687343]
  We propose a methodology for analyzing POMCP policies by inspecting their traces. The proposed method explores local properties of policy behavior to identify unexpected decisions. We evaluate our approach on Tiger, a standard benchmark for POMDPs, and a real-world problem related to mobile robot navigation.
  arXiv  Detail & Related papers  (2020-12-23T15:09:28Z)
• Adaptive Sampling for Best Policy Identification in Markov Decision Processes [79.4957965474334]
  We investigate the problem of best-policy identification in discounted Markov Decision (MDPs) when the learner has access to a generative model. The advantages of state-of-the-art algorithms are discussed and illustrated.
  arXiv  Detail & Related papers  (2020-09-28T15:22:24Z)
• Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure [57.90236104782219]
  We study regret in non-episodic factored Markov decision processes (FMDPs) All existing algorithms make the strong assumption that the factored structure of the FMDP is known to the learner in advance. We provide the first algorithm that learns the structure of the FMDP while minimizing the regret.
  arXiv  Detail & Related papers  (2020-09-13T12:30:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.