Sampled Fictitious Play is Hannan Consistent
暂无分享,去创建一个
[1] James Hannan,et al. 4. APPROXIMATION TO RAYES RISK IN REPEATED PLAY , 1958 .
[2] S. Hart,et al. Simple Adaptive Strategies: From Regret-matching To Uncoupled Dynamics , 2013 .
[3] Wojciech Kotlowski,et al. Follow the Leader with Dropout Perturbations , 2014, COLT.
[4] H. Robbins. A Remark on Stirling’s Formula , 1955 .
[5] D. Fudenberg,et al. The Theory of Learning in Games , 1998 .
[6] Yishay Mansour,et al. From External to Internal Regret , 2005, J. Mach. Learn. Res..
[7] H. Young,et al. Learning dynamics in games with stochastic perturbations , 1995 .
[8] Gábor Lugosi,et al. Internal Regret in On-Line Portfolio Selection , 2005, Machine Learning.
[9] Robert L. Smith,et al. A Fictitious Play Approach to Large-Scale Optimization , 2005, Oper. Res..
[10] Gábor Lugosi,et al. Prediction, learning, and games , 2006 .
[11] Santosh S. Vempala,et al. Efficient algorithms for online decision problems , 2005, Journal of computer and system sciences (Print).
[12] P. Erdös. On a lemma of Littlewood and Offord , 1945 .
[13] Luc Devroye,et al. Prediction by random-walk perturbation , 2013, COLT.