---
title: "Bounded Policy Iteration for Decentralized POMDPs"
authors:
  - "Daniel S. Bernstein"
  - "Eric A. Hansen"
  - "Shlomo Zilberstein"
doi: ""
url: "https://ijcai.org/proceedings/2005/18"
pdf: "https://ijcai.org/proceedings/2005/0018.pdf"
venue: "Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence"
year: 2005
pages: "1287-1291"
track: ""
keywords:
---

# Bounded Policy Iteration for Decentralized POMDPs

Daniel S. Bernstein, Eric A. Hansen, Shlomo Zilberstein

*Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence*, pages 1287-1291.

## Abstract

We present a bounded policy iteration algorithm for infinite-horizon decentralized POMDPs. Policies are represented as joint stochastic finite-state controllers, which consist of a local controller for each agent. We also let a joint controller include a correlation device that allows the agents to correlate their behavior without exchanging information during execution, and show that this leads to improved performance. The algorithm uses a fixed amount of memory, and each iteration is guaranteed to produce a controller with value at least as high as the previous one for all possible initial state distributions. For the case of a single agent, the algorithm reduces to Poupart and Boutilier’s bounded policy iteration for POMDPs.