Machine Learning 

and

Mean Field Games

Seminar series



Online talks at the interface of 

machine learning and mean field games

 

In the past few years, the connections between machine learning and mean field methods have emerged as a fruitful research direction. On the one hand, machine learning methods such as deep learning or reinforcement learning can be used to solve mean field games. On the other hand, mean field techniques can be used to study neural networks or multi-agent reinforcement learning. This seminar series aims at fostering the interactions on these topics. 

 

 

Upcoming talks

TBA

Past talks

June 4, 2024

Bruno Ziliotto

Bayesian learning in Mean Field Games

May 7, 2024

Bruno Gaujal

 Near-Optimal Policies for Weakly Coupled Markov Decision Processes

April 2, 2024

Bora Yongacoglu

 Partially observed n-player mean-field games: Connections to POMDPs and Subjective Equilibrium

March 12, 2024

Batuhan Yardim

When is Mean-Field Reinforcement Learning Tractable and Relevant?

November 28, 2023

Gökçe Dayanikli

Utilizing deep learning and game theory to find optimal policies for societies

November 14, 2023

Desik Rengarajan

 Reinforcement Learning for Mean Field Games with Strategic Complementarities

October 24, 2023

Benjamin Zhang

 A mean-field games laboratory for generative modeling

September 19, 2023

Patrick Benjamin

 Networked Communication for Decentralised Agents in Mean-Field Games

June 6, 2023

Barna Pasztor

 Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning

May 16, 2023

Tamer Başar

Mean Field Games with Elements of Robustness and Learning

March 28, 2023

Niao He

 Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games

March 7, 2023

Panayotis Mertikopoulos

 Learning in nonatomic games

February 7, 2023

Yongzhao Wang

 Empirical Game-Theoretic Analysis for Mean Field Games

January 10, 2023

Zhenjie Ren

 Regularized Mean Field Optimization with Application to Neural Networks

December 6 2022

Yang Chen

Mean Field Game as a Framework for Many-agent Inverse Reinforcement Learning

November 22, 2022

Hamidou Tembine

Data-Driven Mean-Field-Type Games

November 8, 2022

Fabio Camilli

A Mean Field Games approach to cluster analysis

July 5, 2022

Sharon Di

Dynamic Driving and Routing Games for Autonomous Vehicles on Networks: A Mean Field Game Approach

June 21, 2022

Daniel Kious

Finding geodesics on graphs using reinforcement learning

May 31, 2022

Pascal Poupart

 Extending Mean Field Reinforcement Learning to Partially Observable Environments, Agents of Multiple Types and Decentralized Learning

May 17, 2022

Andrea Angiuli

Bridging the gap of reinforcement learning for mean field games and mean field control problems

May 3, 2022

Muhammad Aneeq uz Zaman

Reinforcement Learning for Non-Stationary Discrete-Time Linear-Quadratic Mean-Field Games in Multiple Populations

March 22, 2022

Ruimeng Hu

Convergence of Empirical Measures, Mean-Field Games and Signatures

March 15, 2022

Mérouane Debbah

Distributed Network Design in the Era of Deep Learning

February 15, 2022

Naci Saldi

Learning in Discounted-cost and Average-cost Mean-field Games

January 18, 2022

François Delarue

Exploration Noise for learning linear-quadratic mean field games

December 14, 2021

Kai Cui 

Learning Mean Field Games: Entropy Regularization and Dense Graph Limits

November 23, 2021

Aditya Mahajan

Reinforcement learning in stationary mean-field games

November 16, 2021

Sarah Perrin & Mathieu Laurière

Learning Mean Field Games and Mean Field Control: An Overview

November 2, 2021

Xin Guo

A mean field perspective for multi-agent reinforcement learning

Reach out if you want to participate !

Organisers: 

Romuald Elie (DeepMind), Matthieu Geist (Google Brain), 

Mathieu Laurière (NYU Shanghai, Google Brain), Sarah Perrin (University of Lille), Olivier Pietquin (Google Brain)

Contact: mathieu.lauriere@nyu.edu