Back to activities
ISS Informal Systems Seminar

How to Use Mean-Field Control for Restless Bandits and Weakly Coupled MDPs

iCalendar

Apr 11, 2023   11:00 AM — 12:00 PM

Nicolas Gast INRIA, France

Nicolas Gast

Presentation on YouTube.

Many resource allocation problems can be modeled as « weakly coupled MDPs ». In such a problem, an operator is faced with a population of entities whose state evolves over time. The evolution of the entities are coupled only through the actions of the controller. These problems are in general computationally hard for a finite population of entities but are interestingly easier when the population is infinite. In particular, there exists different LP-based relaxations (including the famous Whittle index) that generally provide near-optimal solutions. The goal of this talk is to introduce these policies, and to present recent results on when they become asymptotically optimal as the number of resources goes to infinity.


Biography: Nicolas Gast is a tenured research scientist at Inria (Grenoble,France) since 2014, and currently visiting MIT for the semester. He graduated from Ecole Normale Superieure (Paris,France) in 2007 and received a Ph.D. from the University of Grenoble in 2010. He was a research fellow at EPFL from 2010 to 2014. His research focuses on the development and the use of stochastic models and optimization methods for the design of control algorithms in large-scale systems.

Peter E. Caines organizer
Aditya Mahajan organizer
Shuang Gao organizer

Location

Hybrid seminar at McGill University
Zoom et salle 603
McConnell Engineering Building
McGill University
3480 rue University

Montréal Québec H3A 0E9
Canada

Associated organization

Centre for intelligent machines (CIM)

Research Axes