Optimality of Decentralized Symmetric Policies for Stochastic Teams with Mean-Field Information Sharing

S Sanjari, N Saldi, S Yüksel - arXiv preprint arXiv:2404.04957, 2024 - arxiv.org
We study a class of stochastic exchangeable teams comprising a finite number of decision
makers (DMs) as well as their mean-field limits involving infinite numbers of DMs. In the finite …

Infinite Horizon Average Cost Optimality Criteria for Mean-Field Control

E Bayraktar, AD Kara - SIAM Journal on Control and Optimization, 2024 - SIAM
We study mean-field control problems in discrete time under the infinite horizon average
cost optimality criteria. We focus on both the finite population and the infinite population …

Ergodic control of a heterogeneous population and application to electricity pricing

Q Jacquet, W van Ackooij, C Alasseur… - 2022 IEEE 61st …, 2022 - ieeexplore.ieee.org
We consider a control problem for a heterogeneous population composed of customers able
to switch at any time between different contracts, depending not only on the tariff conditions …

Mean field reinforcement learning: an optimal control perspective

A Vasileiadis - 2024 - theses.hal.science
The goal of the PhD will be to implement a similar mean field approach to handle MARL.
This idea was investigated, at least for individual agents, in several recent papers. In all of …