Files in this item



application/pdfJiang_Chong.pdf (325kB)
(no description provided)PDF


Title:Parametrized Stochastic Multi-armed Bandits with Binary Rewards
Author(s):Jiang, Chong
Advisor(s):Srikant, Rayadurgam
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):multi-armed bandits
machine learning
Abstract:In this thesis, we consider the problem of multi-armed bandits with a large number of correlated arms. We assume that the arms have Bernoulli distributed rewards, independent across arms and across time, where the probabilities of success are parametrized by known attribute vectors for each arm, as well as an unknown preference vector. For this model, we seek an algorithm with a total regret that is sub-linear in time and independent of the number of arms. We present such an algorithm, which we call the Three-phase Algorithm, and analyze its performance. We show an upper bound on the total regret which applies uniformly in time. The asymptotics of this bound show that for any $f \in \omega(\log(T))$, the total regret can be made to be $O(f(T))$, independent of the number of arms.
Issue Date:2011-01-14
Rights Information:Copyright 2010 Chong Jiang
Date Available in IDEALS:2011-01-14
Date Deposited:December 2

This item appears in the following Collection(s)

Item Statistics