A Novel Point-based Algorithm for Multi-agent Control Using the Common Information Approach

Dengwang Tang, Rahul Jain, Ashutosh Nayyar

Publication date: 9 April 2023

Abstract: The Common Information (CI) approach provides a systematic way to transform a multi-agent stochastic control problem to a single-agent partially observed Markov decision problem (POMDP) called the coordinator's POMDP. However, such a POMDP can be hard to solve due to its extraordinarily large action space. We propose a new algorithm for multi-agent stochastic control problems, called coordinator's heuristic search value iteration (CHSVI), that combines the CI approach and point-based POMDP algorithms for large action spaces. We demonstrate the algorithm through optimally solving several benchmark problems.

Has companion code repository: https://github.com/dwtang/chsvi

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

This page was built for publication: A Novel Point-based Algorithm for Multi-agent Control Using the Common Information Approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6432587)