Principled exploration in sequential decision-making
Ban, Yikun
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/124489
Description
Title
Principled exploration in sequential decision-making
Author(s)
Ban, Yikun
Issue Date
2024-03-11
Director of Research (if dissertation) or Advisor (if thesis)
He, Jingrui
Doctoral Committee Chair(s)
He, Jingrui
Committee Member(s)
Banerjee, Arindam
Jiang, Nan
Xing, Eric P.
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Multi-armed Bandits
Contextual Bandits
Neural Networks
Exploitation and Exploration
Abstract
Interactive Machine Learning (IML) possesses the unique capability to harness feedback from interactions, making it indispensable in a wide array of real-world applications. However, a significant challenge, known as the "exploitation and exploration dilemma," prominently arises within the domain of IML. In this context, learners must not only exploit current information but also explore to uncover potential knowledge for long-term gains. Despite decades of research yielding a rich landscape of algorithms, frameworks, and theories for effectively utilizing collected data to train machine learning models, a fundamental question has remained largely unaddressed: How can IML models systematically make principled exploration for long-term benefits, alongside the full exploitation of current data? This thesis will motivate the exploration of IML by human principles in sequential decision-making, and then present our research efforts in developing principled exploration strategies, including adaptive exploration, collaborative exploration, and customized exploration, and the future directions in trustworthy exploration. The content of this thesis will cover the fundamental algorithms and theories in exploration and show how the exploration strategies impact other machine learning problems and real-world applications.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
