Back to search

University of British Columbia

Beyond learning curves : understanding stochasiticity and learned solution modes in reinforcement learning

Abstract

dc:description

While deep reinforcement learning (Deep RL) algorithms have been used to successfully solve challenging decision making and control tasks, their behavior often remains poorly understood. Studies and comparisons between algorithms are often done through impoverished and partial signals such as learning curves and individual rollout videos. In this work, we follow along a tradition of work which dives deeper into why exactly algorithms produce different rewards from run to run on different tasks. We aim to go beyond learning curves and develop a more holistic view of both the optimization landscape of particular environments and the multimodal behaviors that algorithms produce for given environments. To this end, we develop a set of tools for comparing many runs of deep reinforcement learning algorithms and rollouts from a single policy. We use these to answer a broad range of questions about RL.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wilson, Matthew
Contributors dc:contributor
  • Van de Panne, M. (Michiel), 1965-

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/82765

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Wilson, Matthew. Beyond learning curves : understanding stochasiticity and learned solution modes in reinforcement learning. master's thesis, University of British Columbia, 2022. http://hdl.handle.net/2429/82765