Approachability, fast and slow

Approachability has become a central tool in the analysis of repeated games and online learning. A player plays a repeated vector-valued game against Nature and her objective is to have her long-term average reward inside some target set. The celebrated results of Blackwell provide a 1= p n convergence rate of the expected point-to-set distance if this is achievable, i.e., if the set is approachable. In this paper we provide a characterization for the convergence rates of approachability and show that in some cases a set can be approached with a 1=n rate. Our characterization is solely based on a combination of geometric properties of the set with properties of the repeated game, and not on additional restrictive assumptions on Nature’s behavior.

[1]  Philip Wolfe,et al.  Contributions to the theory of games , 1953 .

[2]  D. Blackwell.  An analog of the minimax theorem for vector payoffs. , 1956 .

[3]  James Hannan,et al.  4. APPROXIMATION TO RAYES RISK IN REPEATED PLAY , 1958 .

[4]  Elon Kohlberg,et al.  Optimal strategies in repeated games with incomplete information , 1975 .

[5]  A. Dawid.  The Well-Calibrated Bayesian , 1982 .

[6]  G. Ziegler.  Lectures on Polytopes , 1994 .

[7]  Robert J. Aumann,et al.  Repeated Games with Incomplete Information , 1995 .

[8]  Dean P. Foster,et al.  A Proof of Calibration Via Blackwell's Approachability Theorem , 1999 .

[9]  S. Hart,et al.  A General Class of Adaptive Strategies , 1999 .

[10]  Christian Schindelhauer,et al.  Discrete Prediction Games with Arbitrary Feedback and Loss , 2001, COLT/EuroCOLT.

[11]  Microeconomics-Charles W. Upton.  Repeated games , 2020, Game Theory.

[12]  Xavier Spinat,et al.  A Necessary and Sufficient Condition for Approachability , 2002, Math. Oper. Res..

[13]  Ingo Steinwart,et al.  Fast Rates for Support Vector Machines , 2005, COLT.

[14]  Nicolò Cesa-Bianchi,et al.  Regret Minimization Under Partial Monitoring , 2006, ITW.

[15]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[16]  A. Tsybakov,et al.  Fast learning rates for plug-in classifiers , 2007, 0708.2321.

[17]  Shie Mannor,et al.  Regret minimization in repeated matrix games with variable stage duration , 2008, Games Econ. Behav..

[18]  Shie Mannor,et al.  Strategies for Prediction Under Imperfect Monitoring , 2007, Math. Oper. Res..

[19]  John N. Tsitsiklis,et al.  Online Learning with Sample Path Constraints , 2009, J. Mach. Learn. Res..

[20]  D. Blackwell.  Controlled Random Walks , 2010 .

[21]  Shie Mannor,et al.  A Geometric Proof of Calibration , 2009, Math. Oper. Res..

[22]  Vianney Perchet,et al.  Approachability of Convex Sets in Games with Partial Monitoring , 2011, J. Optim. Theory Appl..

[23]  Ambuj Tewari,et al.  Online Learning: Stochastic and Constrained Adversaries , 2011, ArXiv.

[24]  Vianney Perchet,et al.  Internal Regret with Partial Monitoring: Calibration-Based Optimal Algorithms , 2011, J. Mach. Learn. Res..

[25]  Ambuj Tewari,et al.  Online Learning: Beyond Regret , 2010, COLT.

[26]  Peter L. Bartlett,et al.  Blackwell Approachability and No-Regret Learning are Equivalent , 2010, COLT.

[27]  Shie Mannor,et al.  Robust approachability and regret minimization in games with partial monitoring , 2011, COLT.

[28]  Csaba Szepesvári,et al.  Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments , 2011, COLT.

[29]  Dean P. Foster,et al.  No Internal Regret via Neighborhood Watch , 2011, AISTATS.

[30]  Vianney Perchet,et al.  Approachability, Regret and Calibration; implications and equivalences , 2013, ArXiv.