Woodroofe's One-Armed Bandit Problem Revisited

We consider the one-armed bandit problem of Woodroofe [J. Amer. Statist. Assoc. 74 (1979) 799-806], which involves sequential sampling from two populations: one whose characteristics are known, and one which depends on an unknown parameter and incorporates a covariate. The goal is to maximize cumulative expected reward. We study this problem in a minimax setting, and develop rate-optimal polices that involve suitable modifications of the myopic rule. It is shown that the regret, as well as the rate of sampling from the inferior population, can be finite or grow at various rates with the time horizon of the problem, depending on "local" properties of the covariate distribution. Proofs rely on martingale methods and information theoretic arguments.

[1]  M. Woodroofe.  A One-Armed Bandit Problem with a Concomitant Variable , 1979 .

[2]  Donald A. Berry,et al.  Bandit Problems: Sequential Allocation of Experiments. , 1986 .

[3]  L. Devroye.  A Course in Density Estimation , 1987 .

[4]  P. W. Jones,et al.  Bandit Problems, Sequential Allocation of Experiments , 1987 .

[5]  M. Clayton.  Covariate models for bernoulli bandits , 1989 .

[6]  Christian M. Ernst,et al.  Multi-armed Bandit Allocation Indices , 1989 .

[7]  Lawrence D. Brown,et al.  Information Inequalities for the Bayes Risk , 1990 .

[8]  J. Bather,et al.  Multi‐Armed Bandit Allocation Indices , 1990 .

[9]  J. Sarkar.  One-Armed Bandit Problems with Covariates , 1991 .

[10]  R. Gill,et al.  Applications of the van Trees inequality : a Bayesian Cramr-Rao bound , 1995 .

[11]  Vladimir Spokoiny,et al.  Deviation probability bound for martingales with applications to statistical estimation , 2000 .

[12]  E. Mammen,et al.  Smooth Discrimination Analysis , 1999 .

[13]  T. Lai.  SEQUENTIAL ANALYSIS: SOME CLASSICAL PROBLEMS AND NEW CHALLENGES , 2001 .

[14]  Yuhong Yang,et al.  RANDOMIZED ALLOCATION WITH NONPARAMETRIC ESTIMATION FOR A MULTI-ARMED BANDIT PROBLEM WITH COVARIATES , 2002 .

[15]  A. Tsybakov,et al.  Introduction à l'estimation non-paramétrique , 2003 .

[16]  A. Tsybakov,et al.  Optimal aggregation of classifiers in statistical learning , 2003 .

[17]  T. Lai,et al.  SELF-NORMALIZED PROCESSES: EXPONENTIAL INEQUALITIES, MOMENT BOUNDS AND ITERATED LOGARITHM LAWS , 2004, math/0410102.

[18]  H. Vincent Poor,et al.  Bandit problems with side observations , 2005, IEEE Transactions on Automatic Control.

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

[20]  T. Lai,et al.  Pseudo-maximization and self-normalized processes , 2007, 0709.2233.

[21]  Assaf Zeevi,et al.  Performance Limitations in Bandit Problems with Side Observations , 2007 .

[22]  H. Robbins.  Some aspects of the sequential design of experiments , 1952 .

[23]  T. L. Lai Andherbertrobbins.  Asymptotically Efficient Adaptive Allocation Rules , 2022 .