Date of this Version
Journal of Machine Learning Research
We present an algorithm which attains O(√T) internal (and thus external) regret for finite games with partial monitoring under the local observability condition. Recently, this condition has been shown by Bartok, Pal, and Szepesvari (2011) to imply the O(√T) rate for partial monitoring games against an i.i.d. opponent, and the authors conjectured that the same holds for non-stochastic adversaries. Our result is in the affirmative, and it completes the characterization of possible rates for finite partial-monitoring games, an open question stated by Cesa-Bianchi, Lugosi, and Stoltz (2006). Our regret guarantees also hold for the more general model of partial monitoring with random signals.
Foster, D. P., & Rakhlin, A. (2012). No Internal Regret via Neighborhood Watch. Journal of Machine Learning Research, 22 382-390. Retrieved from https://repository.upenn.edu/statistics_papers/210
Date Posted: 27 November 2017
This document has been peer reviewed.