A Single Online Agent Can Efficiently Learn Mean Field Games

arXiv:2405.03718v1 Announce Type: new
Abstract: Mean field games (MFGs) are a promising framework for modeling the behavior of large-population systems. However, solving MFGs can be challenging due to the coupling of forward population evolution and backward agent dynamics. Typically, obtaining mean field Nash equilibria (MFNE) involves an iterative approach where the forward and backward processes are solved alternately, known as fixed-point iteration (FPI). This method requires fully observed population propagation and agent dynamics over the entire spatial domain, which could …

abstract agent arxiv behavior cs.ai cs.lg cs.ma dynamics equilibria evolution framework games however iterative learn mean modeling population systems type