Leveraging the Value of Information in POMDP Planning

• URL: http://arxiv.org/abs/2604.01434v1
• Date: Wed, 01 Apr 2026 22:18:55 GMT
• Title: Leveraging the Value of Information in POMDP Planning
• Abstract summary: We introduce a dynamic programming framework that exploits the value of information at each belief.<n>We propose Value of Information Monte Carlo planning (VOIMCP), a Monte Carlo Tree Search algorithm that allocates computational effort more efficiently.<n>We provide theoretical guarantees on the near-optimality of our VOI reasoning framework and derive non-asymptotic convergence bounds for VOIMCP.
• Score: 7.019683407682642
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Partially observable Markov decision processes (POMDPs) offer a principled formalism for planning under state and transition uncertainty. Despite advances made towards solving large POMDPs, obtaining performant policies under limited planning time remains a major challenge due to the curse of dimensionality and the curse of history. For many POMDP problems, the value of information (VOI) - the expected performance gain from reasoning about observations - varies over the belief space. We introduce a dynamic programming framework that exploits this structure by conditionally processing observations based on the value of information at each belief. Building on this framework, we propose Value of Information Monte Carlo planning (VOIMCP), a Monte Carlo Tree Search algorithm that allocates computational effort more efficiently by selectively disregarding observation information when the VOI is low, avoiding unnecessary branching of observations. We provide theoretical guarantees on the near-optimality of our VOI reasoning framework and derive non-asymptotic convergence bounds for VOIMCP. Simulation evaluations demonstrate that VOIMCP outperforms baselines on several POMDP benchmarks.

Related papers

• Optimal sequential decision-making for error propagation mitigation in digital twins [0.0]
  We develop a Markov Decision Process (MDP) in which the inferred regimes serve as states, corrective interventions serve as actions, and a scalar reward takes into consideration the cost-benefit tradeoff between system fidelity and maintenance expense.<n>We then extend the formulation to a Partially Observable MDP (POMDP) that accounts for the imperfect nature of regime classification by maintaining a belief updated via Bayesian filtering.<n>Both formulations are solved via dynamic programming and simulation. We then benchmark two model-free reinforcement learning algorithms, Q-learning and REINFORCE, to assess whether effective policies can be learned without explicit model knowledge.
  arXiv  Detail & Related papers  (2026-04-24T02:36:23Z)
• Sequential Monte Carlo for Policy Optimization in Continuous POMDPs [10.675160254513615]
  We introduce a novel policy optimization framework for continuous partially observable Markov decision processes.<n>Our method casts policy learning as probabilistic inference in a non-Markovian Feynman--Kac model.<n>We demonstrate the effectiveness of our algorithm across standard continuous POMDP benchmarks.
  arXiv  Detail & Related papers  (2025-05-22T14:45:46Z)
• A Finite-State Controller Based Offline Solver for Deterministic POMDPs [18.518047404768378]
  We propose DetMCVI, an adaptation of the Monte Carlo Value Iteration (MCVI) algorithm for DetPOMDPs.<n>DetMCVI solves large problems with a high success rate, outperforming existing baselines for DetPOMDPs.<n>We also verify the performance of the algorithm in a real-world mobile robot forest mapping scenario.
  arXiv  Detail & Related papers  (2025-05-01T15:30:26Z)
• The Lessons of Developing Process Reward Models in Mathematical Reasoning [62.165534879284735]
  Process Reward Models (PRMs) aim to identify and mitigate intermediate errors in the reasoning processes.<n>We develop a consensus filtering mechanism that effectively integrates Monte Carlo (MC) estimation with Large Language Models (LLMs)<n>We release a new state-of-the-art PRM that outperforms existing open-source alternatives.
  arXiv  Detail & Related papers  (2025-01-13T13:10:16Z)
• Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting [56.92178753201331]
  We propose the Observation-Aware Spectral (OAS) estimation technique, which enables the POMDP parameters to be learned from samples collected using a belief-based policy. We show the consistency of the OAS procedure, and we prove a regret guarantee of order $mathcalO(sqrtT log(T)$ for the proposed OAS-UCRL algorithm.
  arXiv  Detail & Related papers  (2024-10-02T08:46:34Z)
• Improved Monte Carlo Planning via Causal Disentanglement for Structurally-Decomposed Markov Decision Processes [0.9768138268100163]
  We introduce the Structurally Decomposed MDP (SD-MDP), which leverages causal disentanglement to partition an MDP's temporal causal graph into independent components.<n>We demonstrate superior policy performance over benchmarks across various logistics and finance domains.
  arXiv  Detail & Related papers  (2024-06-23T16:22:40Z)
• Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach [57.788675205519986]
  We learn high-quality traces from POMDP executions generated by any solver. We exploit data- and time-efficient Indu Logic Programming (ILP) to generate interpretable belief-based policy specifications. We show that learneds expressed in Answer Set Programming (ASP) yield performance superior to neural networks and similar to optimal handcrafted task-specifics within lower computational time.
  arXiv  Detail & Related papers  (2024-02-29T15:36:01Z)
• Nearly Optimal Latent State Decoding in Block MDPs [74.51224067640717]
  In episodic Block MDPs, the decision maker has access to rich observations or contexts generated from a small number of latent states. We are first interested in estimating the latent state decoding function based on data generated under a fixed behavior policy. We then study the problem of learning near-optimal policies in the reward-free framework.
  arXiv  Detail & Related papers  (2022-08-17T18:49:53Z)
• Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes [65.91730154730905]
  In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors. Here we tackle this by considering off-policy evaluation in a partially observed Markov decision process (POMDP) We extend the framework of proximal causal inference to our POMDP setting, providing a variety of settings where identification is made possible.
  arXiv  Detail & Related papers  (2021-10-28T17:46:14Z)
• Exploiting Submodular Value Functions For Scaling Up Active Perception [60.81276437097671]
  In active perception tasks, agent aims to select sensory actions that reduce uncertainty about one or more hidden variables. Partially observable Markov decision processes (POMDPs) provide a natural model for such problems. As the number of sensors available to the agent grows, the computational cost of POMDP planning grows exponentially.
  arXiv  Detail & Related papers  (2020-09-21T09:11:36Z)
• Value of structural health information in partially observable stochastic environments [0.0]
  We introduce and study the theoretical and computational foundations of the Value of Information (VoI) and the Value of Structural Health Monitoring (VoSHM) It is shown that a POMDP policy inherently leverages the notion of VoI to guide observational actions in an optimal way at every decision step.
  arXiv  Detail & Related papers  (2019-12-28T22:18:48Z)

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.