2026-09-21T21:21:21Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/120276 2023-09-05 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Lazebnik, Svetlana 2023-05 application/pdf en text 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 Model-free learning with imitation Walia, Nikash 2023-04-17 Reinforcement Learning Knowledge Distillation 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. Thesis eng https://hdl.handle.net/2142/120276 Copyright 2023 Nikash Walia M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science