# Stick-Breaking Policy Learning in Dec-POMDPs

arXiv: https://arxiv.org/abs/1505.00274 · HTML: https://mlsanity.com/paper/1505.00274/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2015.

## Built on by (most cited first, 3 of 3)

- [Monte-Carlo Search for an Equilibrium in Dec-POMDPs](https://mlsanity.com/paper/2305.11811/) (2023)
- [Bayesian Nonparametric Reinforcement Learning in LTE and Wi-Fi Coexistence](https://mlsanity.com/paper/2105.12249/) (2021)
- [Bayesian Nonparametric Modelling for Model-Free Reinforcement Learning in LTE-LAA and Wi-Fi Coexistence](https://mlsanity.com/paper/2107.02431/) (2021)

## Abstract (arXiv)

Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to represent the local policy of each agent. These variable-size FSCs are constructed using a stick-breaking prior, leading to a new framework called decentralized stick-breaking policy representation (Dec-SBPR). This approach learns the controller parameters with a variational Bayesian algorithm without having to assume that the Dec-POMDP model is available. The performance of Dec-SBPR is demonstrated on several benchmark problems, showing that the algorithm scales to large problems while outperforming other state-of-the-art methods.