{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124489"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124489","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Principled exploration in sequential decision-making","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","abstract_has_math":false,"creators":["Ban, Yikun"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["He, Jingrui","Banerjee, Arindam","Jiang, Nan","Xing, Eric P."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:02Z","subjects":["Multi-armed Bandits","Contextual Bandits","Neural Networks","Exploitation And Exploration"],"languages":["en","eng"],"rights":["Copyright 2024 Yikun Ban"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124489","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["He, Jingrui","Banerjee, Arindam","Jiang, Nan","Xing, Eric P."]},{"key":"dc:creator","label":"Author","values":["Ban, Yikun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-03-11"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Multi-armed Bandits","Contextual Bandits","Neural Networks","Exploitation And Exploration"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2024 Yikun Ban"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124489"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","The student, Yikun Ban, accepted the attached license on 2024-03-06 at 16:36.","The student, Yikun Ban, submitted this Dissertation for approval on 2024-03-06 at 16:47.","This Dissertation was approved for publication on 2024-03-11 at 16:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20227 on 2024-09-16 at 00:42:54","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."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Principled exploration in sequential decision-making"]}]}],"canonical_facts":{"dc:contributor":["He, Jingrui","Banerjee, Arindam","Jiang, Nan","Xing, Eric P."],"dc:creator":["Ban, Yikun"],"dc:date":["2024-05","2024-03-11"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01","The student, Yikun Ban, accepted the attached license on 2024-03-06 at 16:36.","The student, Yikun Ban, submitted this Dissertation for approval on 2024-03-06 at 16:47.","This Dissertation was approved for publication on 2024-03-11 at 16:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20227 on 2024-09-16 at 00:42:54","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."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124489"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Yikun Ban"],"dc:subject":["Multi-armed Bandits","Contextual Bandits","Neural Networks","Exploitation And Exploration"],"dc:title":["Principled exploration in sequential decision-making"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:02Z"}