Abstract | ||
---|---|---|
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. We first present a theoretical convergence analysis of the continuous time Fictitious Play process and prove that the induced exploitability decreases at a rate $O(\frac{1}{t})$. 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. |
Year | Venue | DocType |
---|---|---|
2020 | NIPS 2020 | Conference |
Volume | Citations | PageRank |
33 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Perrin, Sarah | 1 | 0 | 1.35 |
Julien Perolat | 2 | 75 | 12.64 |
Mathieu Laurière | 3 | 11 | 9.66 |
Matthieu Geist | 4 | 385 | 44.31 |
Romuald Elie | 5 | 52 | 10.37 |
Olivier Pietquin | 6 | 664 | 68.60 |