{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/113817"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/113817","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning and adaptation in graphs, networks, and autonomous systems","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms","abstract_has_math":false,"creators":["Lubars, Joseph"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Srikant, Rayadurgam","Beck, Carolyn L","Hu, Bin","Varshney, Lav R"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-04-29T21:34:07Z","date_published":"2022-04-29T21:34:07Z","updated_at":"2026-07-22T22:24:53Z","subjects":["Engineering"],"languages":["en","eng"],"rights":["Copyright 2021 Joseph Lubars"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/113817","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Srikant, Rayadurgam","Beck, Carolyn L","Hu, Bin","Varshney, Lav R"]},{"key":"dc:creator","label":"Author","values":["Lubars, Joseph"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-04-29T21:34:07Z","2021-12","2021-10-06"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["Engineering"]}]},{"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 2021 Joseph Lubars"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/113817"]}]},{"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 2022-04-06 without embargo terms","The student, Joseph Lubars, accepted the attached license on 2021-10-04 at 09:51.","The student, Joseph Lubars, submitted this Dissertation for approval on 2021-10-04 at 10:13.","This Dissertation was approved for publication on 2021-10-06 at 14:23.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17146 on 2022-04-06 at 17:08:50","Made available in DSpace on 2022-04-29T21:34:07Z (GMT). No. of bitstreams: 3 LUBARS-DISSERTATION-2021.pdf: 873153 bytes, checksum: 5bc0fdda870b74f4593b8db2df8ff487 (MD5) LICENSE.txt: 4210 bytes, checksum: 7a96130ec96eb785eebf6bc0c1aa54d0 (MD5) PROQUEST_LICENSE.txt: 4556 bytes, checksum: 016667d681897011f1abcd6a99d48d73 (MD5) Previous issue date: 2021-10-06","Reinforcement learning and adaptation are widely used in a variety of applications, whenever we want to control a dynamical system in some optimal manner. For example, in wireless networking, we can use these tools to learn to route packets more efficiently, leading to lower latency. In games, we can learn better strategies through self-play. In this dissertation, we focus on three problems of reinforcement learning and adaptation. We first consider a theoretical problem in reinforcement learning called optimistic policy iteration (OPI). We prove convergence of a variant of OPI whose convergence properties have been previously unknown. Next, we consider the problem of designing an algorithm to allow a car to autonomously merge onto a highway from an on-ramp. Two broad classes of techniques have been proposed to solve motion planning problems in autonomous driving: Model Predictive Control (MPC) and Reinforcement Learning (RL). In this dissertation, we present an algorithm which blends the model-free RL agent with the MPC solution and show that it provides better trade-offs between a number of relevant metrics: passenger comfort, efficiency, crash rate and robustness. Finally, we analyze a wireless scheduling problem with a limited probing constraint. We show how a throughput optimal solution can be computed, even without knowledge of the channel statistics. Interestingly, although this problem requires adaptability in the face of unknown conditions, we find that reinforcement learning is not needed for optimal performance and may even be harmful if applied without care."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Learning and adaptation in graphs, networks, and autonomous systems"]}]}],"canonical_facts":{"dc:contributor":["Srikant, Rayadurgam","Beck, Carolyn L","Hu, Bin","Varshney, Lav R"],"dc:creator":["Lubars, Joseph"],"dc:date":["2022-04-29T21:34:07Z","2021-12","2021-10-06"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms","The student, Joseph Lubars, accepted the attached license on 2021-10-04 at 09:51.","The student, Joseph Lubars, submitted this Dissertation for approval on 2021-10-04 at 10:13.","This Dissertation was approved for publication on 2021-10-06 at 14:23.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17146 on 2022-04-06 at 17:08:50","Made available in DSpace on 2022-04-29T21:34:07Z (GMT). No. of bitstreams: 3 LUBARS-DISSERTATION-2021.pdf: 873153 bytes, checksum: 5bc0fdda870b74f4593b8db2df8ff487 (MD5) LICENSE.txt: 4210 bytes, checksum: 7a96130ec96eb785eebf6bc0c1aa54d0 (MD5) PROQUEST_LICENSE.txt: 4556 bytes, checksum: 016667d681897011f1abcd6a99d48d73 (MD5) Previous issue date: 2021-10-06","Reinforcement learning and adaptation are widely used in a variety of applications, whenever we want to control a dynamical system in some optimal manner. For example, in wireless networking, we can use these tools to learn to route packets more efficiently, leading to lower latency. In games, we can learn better strategies through self-play. In this dissertation, we focus on three problems of reinforcement learning and adaptation. We first consider a theoretical problem in reinforcement learning called optimistic policy iteration (OPI). We prove convergence of a variant of OPI whose convergence properties have been previously unknown. Next, we consider the problem of designing an algorithm to allow a car to autonomously merge onto a highway from an on-ramp. Two broad classes of techniques have been proposed to solve motion planning problems in autonomous driving: Model Predictive Control (MPC) and Reinforcement Learning (RL). In this dissertation, we present an algorithm which blends the model-free RL agent with the MPC solution and show that it provides better trade-offs between a number of relevant metrics: passenger comfort, efficiency, crash rate and robustness. Finally, we analyze a wireless scheduling problem with a limited probing constraint. We show how a throughput optimal solution can be computed, even without knowledge of the channel statistics. Interestingly, although this problem requires adaptability in the face of unknown conditions, we find that reinforcement learning is not needed for optimal performance and may even be harmful if applied without care."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/113817"],"dc:language":["en","eng"],"dc:rights":["Copyright 2021 Joseph Lubars"],"dc:subject":["Engineering"],"dc:title":["Learning and adaptation in graphs, networks, and autonomous systems"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:53Z"}