Open Access Te Herenga Waka-Victoria University of Wellington
Browse
thesis_access.pdf (9.26 MB)

Absraction for Efficient Reinforcement Learning

Download (9.26 MB)
Version 2 2023-09-25, 02:09
Version 1 2021-12-08, 19:18
thesis
posted on 2023-09-25, 02:09 authored by Telfar, Alexander

Successful reinforcement learning requires large amounts of data, compute, and some luck. We explore the ability of abstraction(s) to reduce these dependencies. Abstractions for reinforcement learning share the goals of this abstract: to capture essential details, while leaving out the unimportant. By throwing away inessential details, there will be less to compute, less to explore, and less variance in observations. But, does this always aid reinforcement learning? More specifically, we start by looking for abstractions that are easily solvable. This leads us to a type of linear abstraction. We show that, while it does allow efficient solutions, it also gives erroneous solutions, in the general case. We then attempt to improve the sample efficiency of a reinforcment learner. We do so by constructing a measure of symmetry and using it as an inductive bias. We design and run experiments to test the advantage provided by this inductive bias, but must leave conclusions to future work.

History

Copyright Date

2020-01-01

Date of Award

2020-01-01

Publisher

Te Herenga Waka—Victoria University of Wellington

Rights License

CC BY-SA 4.0

Degree Discipline

Computer Science

Degree Grantor

Te Herenga Waka—Victoria University of Wellington

Degree Level

Masters

Degree Name

Master of Computer Science

ANZSRC Type Of Activity code

2 STRATEGIC BASIC RESEARCH

Victoria University of Wellington Item Type

Awarded Research Masters Thesis

Language

en_NZ

Victoria University of Wellington School

School of Engineering and Computer Science

Advisors

Browne, Will; McCane, Brendan