English

Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator

Systems and Control 2025-01-06 v4 Systems and Control

Abstract

This paper presents a novel approach to multi-agent reinforcement learning (RL) for linear systems with convex polytopic constraints. Existing work on RL has demonstrated the use of model predictive control (MPC) as a function approximator for the policy and value functions. The current paper is the first work to extend this idea to the multi-agent setting. We propose the use of a distributed MPC scheme as a function approximator, with a structure allowing for distributed learning and deployment. We then show that Q-learning updates can be performed distributively without introducing nonstationarity, by reconstructing a centralized learning update. The effectiveness of the approach is demonstrated on two numerical examples.

Keywords

Cite

@article{arxiv.2312.05166,
  title  = {Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator},
  author = {Samuel Mallick and Filippo Airaldi and Azita Dabiri and Bart De Schutter},
  journal= {arXiv preprint arXiv:2312.05166},
  year   = {2025}
}

Comments

12 pages, 8 figures, accepted for publication in Automatica, code can be found at https://github.com/SamuelMallick/dmpcrl-concept/tree/paper-2023

R2 v1 2026-06-28T13:45:16.891Z