Multi-armed bandits and applications to large datasets

This thesis considers the multi-armed bandit (MAB) problem, both the traditional bandit feedback and graphical bandits when there is side information. Motivated by the Boltzmann exploration algorithm often used in the more general context of reinforcement learning, we present Almost Boltzmann Exploration (ABE) which fixes the under-exploration issue while maintaining an expression similar to Boltzmann exploration. We then present some real world applications of the MAB framework, comparing the performance of ABE with other bandit algorithms on real world datasets.

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

2019

Author dc:creator

• Kong, Seo Taek

Contributors dc:contributor

• Srikant, Rayadurgam

• Multi-Armed Bandits, Boltzmann Exploration

Statement dc:rights

• Copyright 2019 Seo Taek Kong

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/105019

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/105019