MEMOA: Massive Mixtures of Online Agents via Mean-Field Decentralized Nash Equilibria

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Xuwei, Emerson, David B., Tavakoli, Fatemeh, Kratsios, Anastasis
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918486936125440
author Yang, Xuwei
Emerson, David B.
Tavakoli, Fatemeh
Kratsios, Anastasis
author_facet Yang, Xuwei
Emerson, David B.
Tavakoli, Fatemeh
Kratsios, Anastasis
contents In the modern age of large-scale AI, federated learning has become an increasingly important tool for training large populations of AI agents; however, its computational and communication costs can rapidly fail to scale with the number of agents. This is precisely where decentralized agentic strategies shine: each agent acts autonomously, using only its own state together with a minimal summary of the ensemble, namely the mean-field. We derive the unique optimal decentralized policy in closed form. Optimality is characterized through a worst-client/minimax criterion: minimizing the under-performer regret, namely the maximal online cost incurred by the weakest agent in the ensemble. We further prove that the resulting decentralized policy asymptotically converges, in the large-population limit, to the Nash-optimal centralized policy, whose direct computation is not scalable. We use an online weighting mechanism to optimize the server-computed mixture of client predictions, thereby improving the mean prediction in addition to the previously optimized weakest-client prediction. Numerical experiments verify our theoretical guarantees and demonstrate that our decentralized policy typically outperforms natural greedy decentralized baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MEMOA: Massive Mixtures of Online Agents via Mean-Field Decentralized Nash Equilibria
Yang, Xuwei
Emerson, David B.
Tavakoli, Fatemeh
Kratsios, Anastasis
Machine Learning
91A80, 91A16, 93E20, 49N10
I.2.11; I.2.8
In the modern age of large-scale AI, federated learning has become an increasingly important tool for training large populations of AI agents; however, its computational and communication costs can rapidly fail to scale with the number of agents. This is precisely where decentralized agentic strategies shine: each agent acts autonomously, using only its own state together with a minimal summary of the ensemble, namely the mean-field. We derive the unique optimal decentralized policy in closed form. Optimality is characterized through a worst-client/minimax criterion: minimizing the under-performer regret, namely the maximal online cost incurred by the weakest agent in the ensemble. We further prove that the resulting decentralized policy asymptotically converges, in the large-population limit, to the Nash-optimal centralized policy, whose direct computation is not scalable. We use an online weighting mechanism to optimize the server-computed mixture of client predictions, thereby improving the mean prediction in addition to the previously optimized weakest-client prediction. Numerical experiments verify our theoretical guarantees and demonstrate that our decentralized policy typically outperforms natural greedy decentralized baselines.
title MEMOA: Massive Mixtures of Online Agents via Mean-Field Decentralized Nash Equilibria
topic Machine Learning
91A80, 91A16, 93E20, 49N10
I.2.11; I.2.8
url https://arxiv.org/abs/2605.05492