Abstract
We explore the problem of imitation learning (IL) in the context of mean-field games (MFGs), where the goal is to imitate the behavior of a population of agents following a Nash equilibrium policy according to some unknown payoff function. IL in MFGs presents new challenges compared to single-agent IL, particularly when both the reward function and the transition kernel depend on the population distribution. In this paper, departing from the existing literature on IL for MFGs, we introduce a new solution concept called the Nash imitation gap. Then we show that when only the reward depends on the population distribution, IL in MFGs can be reduced to single-agent IL with similar guarantees. However, when the dynamics is population-dependent, we provide a novel upper-bound that suggests IL is harder in this setting. To address this issue, we propose a new adversarial formulation where the reinforcement learning problem is replaced by a mean-field control (MFC) problem, suggesting progress in IL within MFGs may have to build upon MFC. Show more
Publication status
publishedExternal links
Book title
Advances in Neural Information Processing Systems 36Pages / Article No.
Publisher
CurranEvent
Subject
Machine Learning (cs.LG); Computer Science and Game Theory (cs.GT); FOS: Computer and information sciencesOrganisational unit
09729 - He, Niao / He, Niao
Related publications and datasets
Is new version of: https://openreview.net/forum?id=RPFd3D3P3L
Notes
Poster presented on December 13, 2023.More
Show all metadata
ETH Bibliography
yes
Altmetrics