AISep 17, 2021

Solving infinite-horizon Dec-POMDPs using Finite State Controllers within JESP

arXiv:2109.08755v18 citations
Originality Incremental advance
AI Analysis

This work addresses multi-agent planning under uncertainty, offering an incremental extension to existing methods for researchers in AI and robotics.

The paper tackles solving infinite-horizon decentralized POMDPs by adapting the JESP algorithm to use finite state controllers instead of policy trees, enabling Nash equilibrium search in collaborative planning problems.

This paper looks at solving collaborative planning problems formalized as Decentralized POMDPs (Dec-POMDPs) by searching for Nash equilibria, i.e., situations where each agent's policy is a best response to the other agents' (fixed) policies. While the Joint Equilibrium-based Search for Policies (JESP) algorithm does this in the finite-horizon setting relying on policy trees, we propose here to adapt it to infinite-horizon Dec-POMDPs by using finite state controller (FSC) policy representations. In this article, we (1) explain how to turn a Dec-POMDP with $N-1$ fixed FSCs into an infinite-horizon POMDP whose solution is an $N^\text{th}$ agent best response; (2) propose a JESP variant, called \infJESP, using this to solve infinite-horizon Dec-POMDPs; (3) introduce heuristic initializations for JESP aiming at leading to good solutions; and (4) conduct experiments on state-of-the-art benchmark problems to evaluate our approach.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes