# Leveraging the Value of Information in POMDP Planning

arXiv: https://arxiv.org/abs/2604.01434 · HTML: https://mlsanity.com/paper/2604.01434/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [DESPOT: Online POMDP Planning with Regularization](https://mlsanity.com/paper/1609.03250/) (2016)
- [Online algorithms for POMDPs with continuous state, action, and observation spaces](https://mlsanity.com/paper/1709.06196/) (2017)
- [Online Planning Algorithms for POMDPs](https://mlsanity.com/paper/1401.3436/) (2014)
- [Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning](https://mlsanity.com/paper/1801.04099/) (2018)
- [Value of Information and Reward Specification in Active Inference and POMDPs](https://mlsanity.com/paper/2408.06542/) (2024)
- [Increasing the Value of Information During Planning in Uncertain Environments](https://mlsanity.com/paper/2409.13754/) (2024)

## Abstract (arXiv)

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.