1Hannan J. Approximation to Bayes Risk in Repeated Play [M]. In: Dresher Met al (eds) Contributions to The Theory of Games III. Princ- eton University Press, Princeton, 1957.
2Auer P, Cesa-Bianchi N, Freund Y, et al. The Nonstochastic Multi- armed Bandit Problem [J]. SIAM J.Comput, 2002, 32 (1).
3Fudenberg D, Levine D K. Conditional Universal Consistency [J]. Games Econ. Behav, 1999,(29).
4Fudenberg D, Levine D K. An Easier Way to Calibrate. Games Econ [J]. Games Econ. Behav, 1999,(29).
5Nahum-Shimkin. Regret Minimization in Repeated Matrix Games With Variable Stage Duration [J]. Games and Economic Behavior, 2008 (63).
