Optimality of Decentralized Symmetric Policies for Stochastic Teams with Mean-Field Information Sharing
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 …
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 …
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
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 …
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 …
This idea was investigated, at least for individual agents, in several recent papers. In all of …