Machine Learning
and
Mean Field Games
Seminar series
Seminar series
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.
Bayesian learning in Mean Field Games
Near-Optimal Policies for Weakly Coupled Markov Decision Processes
Partially observed n-player mean-field games: Connections to POMDPs and Subjective Equilibrium
When is Mean-Field Reinforcement Learning Tractable and Relevant?
Utilizing deep learning and game theory to find optimal policies for societies
Reinforcement Learning for Mean Field Games with Strategic Complementarities
A mean-field games laboratory for generative modeling
Networked Communication for Decentralised Agents in Mean-Field Games
Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning
Mean Field Games with Elements of Robustness and Learning
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
Learning in nonatomic games
Empirical Game-Theoretic Analysis for Mean Field Games
Regularized Mean Field Optimization with Application to Neural Networks
Mean Field Game as a Framework for Many-agent Inverse Reinforcement Learning
Data-Driven Mean-Field-Type Games
A Mean Field Games approach to cluster analysis
Dynamic Driving and Routing Games for Autonomous Vehicles on Networks: A Mean Field Game Approach
Finding geodesics on graphs using reinforcement learning
Extending Mean Field Reinforcement Learning to Partially Observable Environments, Agents of Multiple Types and Decentralized Learning
Bridging the gap of reinforcement learning for mean field games and mean field control problems
Reinforcement Learning for Non-Stationary Discrete-Time Linear-Quadratic Mean-Field Games in Multiple Populations
Convergence of Empirical Measures, Mean-Field Games and Signatures
Distributed Network Design in the Era of Deep Learning
Learning in Discounted-cost and Average-cost Mean-field Games
Exploration Noise for learning linear-quadratic mean field games
Learning Mean Field Games: Entropy Regularization and Dense Graph Limits
Reinforcement learning in stationary mean-field games
Learning Mean Field Games and Mean Field Control: An Overview
A mean field perspective for multi-agent reinforcement learning
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