暂无分享,去创建一个
Multi-agent games are becoming an increasing prevalent formalism for the study of electronic commerce and auctions. The speed at which transactions can take place and the growing complexity of electronic marketplaces makes the study of computationally simple agents an appealing direction. In this work, we analyze the behavior of agents that incrementally adapt their strategy through gradient ascent on expected payoff, in the simple setting of two-player, two-action, iterated general-sum games, and present a surprising result. We show that either the agents will converge to Nash equilibrium, or if the strategies themselves do not converge, then their average payoffs will nevertheless converge to the payoffs of a Nash equilibrium.
[1] Jörgen W. Weibull,et al. Evolutionary Game Theory , 1996 .
[2] E. Kalai,et al. Rational Learning Leads to Nash Equilibrium , 1993 .
[3] Hervé Reinhard,et al. Differential equations: Foundations and applications , 1986 .
[4] Ronitt Rubinfeld,et al. Efficient algorithms for learning to play repeated games against computationally bounded adversaries , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.