Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications

07/05/2020
by   Sarah Perrin, et al.
5

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, γ-discounted), allowing in particular for the introduction of an additional common noise. We first present a theoretical convergence analysis of the continuous time Fictitious Play process and prove that the induced exploitability decreases at a rate O(1/t). Such analysis emphasizes the use of exploitability as a relevant metric for evaluating the convergence towards a Nash equilibrium in the context of Mean Field Games. These theoretical contributions are supported by numerical experiments provided in either model-based or model-free settings. We provide hereby for the first time converging learning dynamics for Mean Field Games in the presence of common noise.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 8

10/08/2020

Provable Fictitious Play for General Mean-Field Games

We propose a reinforcement learning algorithm for stationary mean-field ...
07/02/2021

Exploration noise for learning linear-quadratic mean field games

The goal of this paper is to demonstrate that common noise may serve as ...
12/02/2021

Empirical Game-Theoretic Analysis in Mean Field Games

In this study, we demonstrate how empirical game-theoretical analysis (E...
02/28/2021

Scaling up Mean Field Games with Online Mirror Descent

We address scaling up equilibrium computation in Mean Field Games (MFGs)...
06/06/2021

Signatured Deep Fictitious Play for Mean Field Games with Common Noise

Existing deep learning methods for solving mean-field games (MFGs) with ...
02/14/2012

Factored Filtering of Continuous-Time Systems

We consider filtering for a continuous-time, or asynchronous, stochastic...
06/24/2020

Teamwise Mean Field Competitions

This paper studies competitions with rank-based reward among a large num...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.