English

Learning in Mean Field Games: the Fictitious Play

Optimization and Control 2015-08-03 v2

Abstract

Mean Field Game systems describe equilibrium configurations in differential games with infinitely many infinitesimal interacting agents. We introduce a learning procedure (similar to the Fictitious Play) for these games and show its convergence when the Mean Field Game is potential.

Keywords

Cite

@article{arxiv.1507.06280,
  title  = {Learning in Mean Field Games: the Fictitious Play},
  author = {Pierre Cardaliaguet and Saeed Hadikhanloo},
  journal= {arXiv preprint arXiv:1507.06280},
  year   = {2015}
}