Principled exploration in sequential decision-making

Ban, Yikun

Permalink

https://hdl.handle.net/2142/124489 Copy

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

Language

eng

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.

Graduation Semester

2024-05

Type of Resource

Text

Handle URL

https://hdl.handle.net/2142/124489

Copyright and License Information

Copyright 2024 Yikun Ban

Owning Collections