Model-free learning with imitation

Walia, Nikash

Permalink

https://hdl.handle.net/2142/120276 Copy

Description

Title

Model-free learning with imitation

Author(s)

Walia, Nikash

Issue Date

2023-04-17

Director of Research (if dissertation) or Advisor (if thesis)

Lazebnik, Svetlana

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Reinforcement learning
• Knowledge distillation

Abstract

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.

Graduation Semester

2023-05

Type of Resource

Thesis

Copyright and License Information

Copyright 2023 Nikash Walia

Owning Collections