Back to search

University of Waterloo

Towards Global Reinforcement Learning

Abstract

dc:description.abstract

Sequential decision making under uncertainty is a ubiquitous problem. In everyday situations we are faced with a series of decisions that aim to maximize the probability of achieving some goal. However, decision outcomes are often uncertain and it is not always immediately evident how to determine if one decision is better than another. The Reinforcement Learning framework overcomes this difficulty by learning to make optimal decisions based on interactions with the environment. One drawback of Reinforcement Learning is that it requires too much data (interactions) to learn from scratch. For this reason, current approaches attempt to incorporate prior information in order to simplify the learning process. However, this is usually accomplished by making problem-specific assumptions, which limit generalizability of the approaches to other problems. This thesis presents the first steps towards a new framework that incorporates and exploits broad prior knowledge in a principled way. It uses Constraint Satisfaction and Bayesian techniques to construct and update a belief over the environment, as well as over good decisions. This allows for incorporating broad types of prior knowledge without limiting generalizability. Preliminary experiments show that the framework's algorithms work well on toy problems in simulation and encourage further research on real-world problems.

Degree

thesis:*
Grantor dc:publisher
University of Waterloo
Year dc:date.issued
2008

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Milen, Pavlov

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/10012/3671

Chain of custody

source
Harvested from
University of Waterloo
Base URL
dspacemainprd01.lib.uwaterloo.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Milen, Pavlov. Towards Global Reinforcement Learning. University of Waterloo, 2008. http://hdl.handle.net/10012/3671