2026-09-19T12:26:15Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/121362 2023-12-13 col_2142_5131 col_2142_14800 com_2142_5130 com_2142_14799 com_2142_234

Hovakimyan, Naira 2023-08 application/pdf en text Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01 The student, Sambhu Harimanas Karumanchi, accepted the attached license on 2023-07-12 at 22:42. The student, Sambhu Harimanas Karumanchi, submitted this Thesis for approval on 2023-07-12 at 23:02. This Thesis was approved for publication on 2023-07-17 at 16:41. DSpace SAF Submission Ingestion Package generated from Vireo submission #19669 on 2023-12-04 at 17:18:39 2023-07-17 Robust Adaptive Control Reinforcement Learning We introduce L1-MBRL, a control-theoretic augmentation scheme for Model-Based Reinforcement Learning (MBRL) algorithms. Unlike model-free approaches, MBRL algorithms learn a model of the transition function using data and use it to design a control input. Our approach approximates the transition function along each trajectory with a control-affine model to generate a control input augmentation that perturbs the input produced by the underlying MBRL policy. The perturbation produced by the L1 adaptive control is designed to enhance the robustness of the system against uncertainties. Importantly, the proposed L1 adaptive control-based learning scheme is agnostic to the choice of MBRL algorithm and can be integrated seamlessly with many model-based RL systems in practice. The method exhibits superior performance and sample efficiency on multiple MuJoCo environments, both with and without system noise, as demonstrated by our numerical simulations. Text eng https://hdl.handle.net/2142/121362 Copyright 2023 Sambhu Harimanas Karumanchi Robust model-based reinforcement learning using L1 adaptive control Karumanchi, Sambhu Harimanas M.S. Thesis Aerospace Engineering University of Illinois at Urbana-Champaign Aerospace Engineering