Stochastic Nash Equilibrium Seeking for Games with General Nonlinear Payoffs
Extremum seeking is extended from standard multi-input optimization problems to multi-player non-cooperative games. The players do not have knowledge of the payoff functions and only measure their own payoff values. The players are also unaware of the other players’ actions. Extremum seeking is shown to achieve convergence to the Nash equilibrium of the underlying static game.
KeywordsAssure Sine Nash
- 38.Foster DP, Young HP (2006) Regret testing: learning to play Nash equilibrium without knowing you have an opponent. Theor Econ 1:341–367 Google Scholar
- 54.Jafari A, Greenwald A, Gondek D, Ercal G (2001) On no-regret learning, fictitious play, and Nash equilibrium. In: Proceedings of the 18th international conference on machine learning Google Scholar
- 72.Krstic M, Frihauf P, Krieger J, Başar T (2010) Nash eqilibrium seeking with finitely- and infinitely-many players. In: Proceedings of the 8th IFAC symposium on nonlinear control systems, Bologna, Italy Google Scholar
- 136.Stanković MS, Johansson KH, Stipanović DM (2010) Distributed seeking of Nash equilibrium in mobile sensor networks. In: Proceedings of IEEE conference on decision and control, Atlanta, GA, USA, December 15–17, pp 5598–5603 Google Scholar
- 150.Zhu M, Martinez S (2010) Distributed coverage games for mobile visual sensor networks. SIAM J Control Optim (submitted). Available at http://arxiv.org/abs/1002.0367