Parametrized Stochastic Multi-armed Bandits with Binary Rewards

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 ω(\log(T)), the total regret can be made to be $O(f(T))$, independent of the number of arms.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2011

Author dc:creator

• Jiang, Chong

Contributors dc:contributor

• Srikant, Rayadurgam

• machine learning
• multi-armed bandits

Statement dc:rights

• Copyright 2010 Chong Jiang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/18352

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/18352