Back to search

University of British Columbia

Combining spatial hints with policy reuse in a reinforcement learning agent

Abstract

dc:description

In this dissertation, we study the problem of knowledge reuse by a reinforcement learning agent. We are interested in how an agent can exploit policies that were learned in the past to learn a new task more efficiently in the present. Our approach is to elicit spatial hints from an expert suggesting the world states in which each existing policy should be more relevant to the new task. By using these hints with domain exploration, the agent is able to detect those portions of existing policies that are beneficial to the new task, therefore learning a new policy more efficiently. We call our approach Spatial Hints Policy Reuse (SHPR). Experiments demonstrate the effectiveness and robustness of our method. Our results encourage further study investigating how much more efficacy can be gained from the elicitation of very simple advice from humans.

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
2010

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • da Silva, Bruno Norberto

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/27708

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

da Silva, Bruno Norberto. Combining spatial hints with policy reuse in a reinforcement learning agent. master's thesis, University of British Columbia, 2010. http://hdl.handle.net/2429/27708