ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2203.00035
18
9

Can Mean Field Control (MFC) Approximate Cooperative Multi Agent Reinforcement Learning (MARL) with Non-Uniform Interaction?

28 February 2022
Washim Uddin Mondal
Vaneet Aggarwal
S. Ukkusuri
ArXivPDFHTML
Abstract

Mean-Field Control (MFC) is a powerful tool to solve Multi-Agent Reinforcement Learning (MARL) problems. Recent studies have shown that MFC can well-approximate MARL when the population size is large and the agents are exchangeable. Unfortunately, the presumption of exchangeability implies that all agents uniformly interact with one another which is not true in many practical scenarios. In this article, we relax the assumption of exchangeability and model the interaction between agents via an arbitrary doubly stochastic matrix. As a result, in our framework, the mean-field `seen' by different agents are different. We prove that, if the reward of each agent is an affine function of the mean-field seen by that agent, then one can approximate such a non-uniform MARL problem via its associated MFC problem within an error of e=O(1N[∣X∣+∣U∣])e=\mathcal{O}(\frac{1}{\sqrt{N}}[\sqrt{|\mathcal{X}|} + \sqrt{|\mathcal{U}|}])e=O(N​1​[∣X∣​+∣U∣​]) where NNN is the population size and ∣X∣|\mathcal{X}|∣X∣, ∣U∣|\mathcal{U}|∣U∣ are the sizes of state and action spaces respectively. Finally, we develop a Natural Policy Gradient (NPG) algorithm that can provide a solution to the non-uniform MARL with an error O(max⁡{e,ϵ})\mathcal{O}(\max\{e,\epsilon\})O(max{e,ϵ}) and a sample complexity of O(ϵ−3)\mathcal{O}(\epsilon^{-3})O(ϵ−3) for any ϵ>0\epsilon >0ϵ>0.

View on arXiv
Comments on this paper