{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/120276"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/120276","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Model-free learning with imitation","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","abstract_has_math":false,"creators":["Walia, Nikash"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Lazebnik, Svetlana"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-05","date_published":"2023-05","updated_at":"2026-07-22T22:24:57Z","subjects":["Reinforcement Learning","Knowledge Distillation"],"languages":["en","eng"],"rights":["Copyright 2023 Nikash Walia"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/120276","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lazebnik, Svetlana"]},{"key":"dc:creator","label":"Author","values":["Walia, Nikash"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-05","2023-04-17"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["Reinforcement Learning","Knowledge Distillation"]}]},{"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 2023 Nikash Walia"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/120276"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","The student, Nikash Walia, accepted the attached license on 2023-04-17 at 11:51.","The student, Nikash Walia, submitted this Thesis for approval on 2023-04-17 at 12:28.","This Thesis was approved for publication on 2023-04-17 at 16:10.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19010 on 2023-09-01 at 17:08:49","Optimizing sample efficiency, or the experience needed in an environment to gain satisfactory performance, is a core challenge for developing reinforcement learning agents. While imitation learning resolves this issue, it is constrained by expert performance. On the other hand, model-based strategies, which learn a world model of the environment, typically fail to approach the asymptotic performance of model-free approaches. In this thesis, we focus on combining imitation learning with model-free reinforcement learning to maximize sample efficiency and achieve higher asymptotic performance. We propose an intuitive approach to leveraging the strengths of each paradigm to produce higher rewards over a fixed number of frames when observing learned experts. We further investigate our method’s applicability to knowledge distillation for reduced-complexity agents. These studies and results lay the foundation for further study which will benefit model-free reinforcement learning as a whole."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Model-free learning with imitation"]}]}],"canonical_facts":{"dc:contributor":["Lazebnik, Svetlana"],"dc:creator":["Walia, Nikash"],"dc:date":["2023-05","2023-04-17"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","The student, Nikash Walia, accepted the attached license on 2023-04-17 at 11:51.","The student, Nikash Walia, submitted this Thesis for approval on 2023-04-17 at 12:28.","This Thesis was approved for publication on 2023-04-17 at 16:10.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19010 on 2023-09-01 at 17:08:49","Optimizing sample efficiency, or the experience needed in an environment to gain satisfactory performance, is a core challenge for developing reinforcement learning agents. While imitation learning resolves this issue, it is constrained by expert performance. On the other hand, model-based strategies, which learn a world model of the environment, typically fail to approach the asymptotic performance of model-free approaches. In this thesis, we focus on combining imitation learning with model-free reinforcement learning to maximize sample efficiency and achieve higher asymptotic performance. We propose an intuitive approach to leveraging the strengths of each paradigm to produce higher rewards over a fixed number of frames when observing learned experts. We further investigate our method’s applicability to knowledge distillation for reduced-complexity agents. These studies and results lay the foundation for further study which will benefit model-free reinforcement learning as a whole."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/120276"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Nikash Walia"],"dc:subject":["Reinforcement Learning","Knowledge Distillation"],"dc:title":["Model-free learning with imitation"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:57Z"}