Paper Info
Title
Concave Utility Reinforcement Learning: The Mean-field Game Viewpoint.
Abstract
Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but also imitation learning and exploration, among others. Yet, this more general paradigm invalidates the classical Bellman equations, and calls for new algorithms. Mean-field Games (MFGs) are a continuous approximation of many-agent RL. They consider the limit case of a continuous distribution of identical agents, anonymous with symmetric interests, and reduce the problem to the study of a single representative agent in interaction with the full population. Our core contribution consists in showing that CURL is a subclass of MFGs. We think this important to bridge together both communities. It also allows to shed light on aspects of both fields: we show the equivalence between concavity in CURL and monotonicity in the associated MFG, between optimality conditions in CURL and Nash equilibrium in MFG, or that Fictitious Play (FP) for this class of MFGs is simply Frank-Wolfe, bringing the first convergence rate for discrete-time FP for MFGs. We also experimentally demonstrate that, using algorithms recently introduced for solving MFGs, we can address the CURL problem more efficiently.
Year
Venue
DocType
2022
International Joint Conference on Autonomous Agents and Multi-agent Systems
Conference
Citations 
PageRank 
References 
0
0.34
0
Authors
8
Name
Order
Citations
PageRank
Matthieu Geist138544.31
Julien Perolat27512.64
Mathieu Laurière3119.66
Romuald Elie45210.37
Sarah Perrin501.01
Olivier Bachem6253.05
Rémi Munos72240157.06
Olivier Pietquin866468.60