no code implementations • 17 Mar 2024 • Muhammad Aneeq uz Zaman, Alec Koppel, Mathieu Laurière, Tamer Başar
This MFTG NE is then shown to be $\mathcal{O}(1/M)$-NE for the finite population game where $M$ is a lower bound on the number of agents in each team.
1 code implementation • 8 Mar 2024 • Asaf Cohen, Mathieu Laurière, Ethan Zell
This paper proposes and analyzes two neural network methods to solve the master equation for finite-state mean field games (MFGs).
no code implementations • 12 Feb 2024 • Mathieu Laurière, Ludovic Tangpi, Xuchen Zhou
By passing to the limit, a game with a continuum of players is obtained, in which the interactions are through a graphon.
1 code implementation • 17 Dec 2023 • Kai Cui, Gökçe Dayanıklı, Mathieu Laurière, Matthieu Geist, Olivier Pietquin, Heinz Koeppl
We propose a novel discrete time version of major-minor MFGs (M3FGs), along with a learning algorithm based on fictitious play and partitioning the probability simplex.
no code implementations • 17 Mar 2023 • Ruimeng Hu, Mathieu Laurière
Recently, computational methods based on machine learning have been developed for solving stochastic control problems and games.
no code implementations • 13 Mar 2023 • Noufel Frikha, Maximilien Germain, Mathieu Laurière, Huyên Pham, Xuanye Song
We study policy gradient for mean-field control in continuous time in a reinforcement learning setting.
no code implementations • 28 Feb 2023 • Sebastian Baudelet, Brieuc Frénais, Mathieu Laurière, Amal Machtalay, Yuchen Zhu
The first one is based on directly learning an optimal control.
no code implementations • 25 May 2022 • Mathieu Laurière, Sarah Perrin, Julien Pérolat, Sertan Girgin, Paul Muller, Romuald Élie, Matthieu Geist, Olivier Pietquin
Non-cooperative and cooperative games with a very large number of players have many applications but remain generally intractable when the number of players increases.
no code implementations • 22 Mar 2022 • Mathieu Laurière, Sarah Perrin, Sertan Girgin, Paul Muller, Ayush Jain, Theophile Cabannes, Georgios Piliouras, Julien Pérolat, Romuald Élie, Olivier Pietquin, Matthieu Geist
One limiting factor to further scale up using RL is that existing algorithms to solve MFGs require the mixing of approximated quantities such as strategies or $q$-values.
no code implementations • 20 Sep 2021 • Sarah Perrin, Mathieu Laurière, Julien Pérolat, Romuald Élie, Matthieu Geist, Olivier Pietquin
Mean Field Games (MFGs) can potentially scale multi-agent systems to extremely large populations of agents.
no code implementations • 14 Sep 2021 • Mathieu Laurière, Gilles Pagès, Olivier Pironneau
Fishing quotas are unpleasant but efficient to control the productivity of a fishing site.
no code implementations • 9 Jul 2021 • René Carmona, Mathieu Laurière
Financial markets and more generally macro-economic models involve a large number of individuals interacting through variables such as prices resulting from the aggregate behavior of all the agents.
no code implementations • 7 Jun 2021 • Matthieu Geist, Julien Pérolat, Mathieu Laurière, Romuald Elie, Sarah Perrin, Olivier Bachem, Rémi Munos, Olivier Pietquin
Mean-field Games (MFGs) are a continuous approximation of many-agent RL.
no code implementations • 17 May 2021 • Sarah Perrin, Mathieu Laurière, Julien Pérolat, Matthieu Geist, Romuald Élie, Olivier Pietquin
We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals.
1 code implementation • 28 Feb 2021 • Julien Perolat, Sarah Perrin, Romuald Elie, Mathieu Laurière, Georgios Piliouras, Matthieu Geist, Karl Tuyls, Olivier Pietquin
We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD).
no code implementations • 2 Sep 2020 • René Carmona, Kenza Hamidouche, Mathieu Laurière, Zongjun Tan
In particular, the case in which the transition and utility functions depend on the state, the action of the controllers, and the mean of the state and the actions, is investigated.
no code implementations • 1 Sep 2020 • René Carmona, Kenza Hamidouche, Mathieu Laurière, Zongjun Tan
In particular, the case in which the transition and utility functions depend on the state, the action of the controllers, and the mean of the state and the actions, is investigated.
1 code implementation • NeurIPS 2020 • Sarah Perrin, Julien Perolat, Mathieu Laurière, Matthieu Geist, Romuald Elie, Olivier Pietquin
In this paper, we deepen the analysis of continuous time Fictitious Play learning algorithm to the consideration of various finite state Mean Field Game settings (finite horizon, $\gamma$-discounted), allowing in particular for the introduction of an additional common noise.
no code implementations • 24 Jun 2020 • Andrea Angiuli, Jean-Pierre Fouque, Mathieu Laurière
We present a Reinforcement Learning (RL) algorithm to solve infinite horizon asymptotic Mean Field Game (MFG) and Mean Field Control (MFC) problems.
no code implementations • 17 Jun 2020 • Laura Leal, Mathieu Laurière, Charles-Albert Lehalle
The issue of scarcity of financial data is solved by transfer learning: the neural network is first trained on trajectories generated thanks to a Monte-Carlo scheme, leading to a good initialization before training on historical trajectories.
no code implementations • 10 Feb 2020 • Haoyang Cao, Xin Guo, Mathieu Laurière
Generative adversarial networks (GANs) have enjoyed tremendous success in image generation and processing, and have recently attracted growing interests in financial modelings.
no code implementations • 28 Oct 2019 • René Carmona, Mathieu Laurière, Zongjun Tan
We study infinite horizon discounted Mean Field Control (MFC) problems with common noise through the lens of Mean Field Markov Decision Processes (MFMDP).
no code implementations • 9 Oct 2019 • René Carmona, Mathieu Laurière, Zongjun Tan
We investigate reinforcement learning for mean field control problems in discrete time, which can be viewed as Markov decision processes for a large number of exchangeable agents interacting in a mean field manner.
no code implementations • 5 Aug 2019 • René Carmona, Mathieu Laurière
The second method tackles a generic forward-backward stochastic differential equation system (FBSDE) of McKean-Vlasov type, and relies on suitable reformulation as a mean field control problem.
no code implementations • 13 Jul 2019 • René Carmona, Mathieu Laurière
Finally, we illustrate the fact that, although the first algorithm is specifically designed for mean field control problems, the second one is more general and can also be applied to the partial differential equation systems arising in the theory of mean field games.
no code implementations • 4 Jul 2019 • Romuald Elie, Julien Pérolat, Mathieu Laurière, Matthieu Geist, Olivier Pietquin
In order to design scalable algorithms for systems with a large population of interacting agents (e. g. swarms), this paper focuses on Mean Field MAS, where the number of agents is asymptotically infinite.