Title :
Bandit problems with side observations
Author :
Wang, Chih-Chun ; Kulkarni, Sanjeev R. ; Poor, H. Vincent
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
fDate :
3/1/2005 12:00:00 AM
Abstract :
An extension of the traditional two-armed bandit problem is considered, in which the decision maker has access to some side information before deciding which arm to pull. At each time t, before making a selection, the decision maker is able to observe a random variable Xt that provides some information on the rewards to be obtained. The focus is on finding uniformly good rules (that minimize the growth rate of the inferior sampling time) and on quantifying how much the additional information helps. Various settings are considered and for each setting, lower bounds on the achievable inferior sampling time are developed and asymptotically optimal adaptive schemes achieving these lower bounds are constructed.
Keywords :
decision theory; asymptotically optimal adaptive schemes; bandit problems; decision maker; side observations; Arm; Bayesian methods; History; Information technology; Optimal control; Random variables; Sampling methods; Statistical distributions; Adaptive; allocation rule; asymptotic; efficient; inferior sampling time; side information; two-armed bandit;
Journal_Title :
Automatic Control, IEEE Transactions on
DOI :
10.1109/TAC.2005.844079