# Improved POMDP Tree Search Planning with Prioritized Action Branching

arXiv: https://arxiv.org/abs/2010.03599 · HTML: https://mlsanity.com/paper/2010.03599/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 2 of 2)

- [BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations](https://mlsanity.com/paper/2306.00249/) (2023)
- [Achieving mouse-level strategic evasion performance using real-time computational planning](https://mlsanity.com/paper/2211.02700/) (2022)

## Abstract (arXiv)

Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. This paper proposes a method called PA-POMCPOW to sample a subset of the action space that provides varying mixtures of exploitation and exploration for inclusion in a search tree. The proposed method first evaluates the action space according to a score function that is a linear combination of expected reward and expected information gain. The actions with the highest score are then added to the search tree during tree expansion. Experiments show that PA-POMCPOW is able to outperform existing state-of-the-art solvers on problems with large discrete action spaces.