Learning in Mean Field Games: the Fictitious Play

doi:https://doi.org/10.48550/arxiv.1507.06280

Open AccessPreprint10.48550/arxiv.1507.06280

Learning in Mean Field Games: the Fictitious Play

Pierre Cardaliaguet,Saeed Hadikhanloo-2015-07-22-arXiv (Cornell University)

TL;DRAbstract

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

Chat with Paper

AI Agents for this Paper

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

Keywords

Fictitious playField (mathematics)Computer sciencePsychologyMathematicsMathematical economicsGame theory

Chat

Click to start Chat