Using Reinforcement Learning in Partial Order Plan Space Metadata
Metadata describes a digital item, providing (if known) such information as creator, publisher, contents, size, relationship to other resources, and more. Metadata may also contain "preservation" components that help us to maintain the integrity of digital files over time.
Title
- Main Title Using Reinforcement Learning in Partial Order Plan Space
Creator
-
Author: Ceylan, HakanCreator Type: Personal
Contributor
-
Chair: Swigger, Kathleen M.Contributor Type: PersonalContributor Info: Major Professor
-
Committee Member: Brazile, RobertContributor Type: Personal
-
Committee Member: Mihalcea, Rada, 1974-Contributor Type: Personal
Publisher
-
Name: University of North TexasPlace of Publication: Denton, Texas
Date
- Creation: 2006-05
- Digitized: 2008-04-22
Language
- English
Description
- Content Description: Partial order planning is an important approach that solves planning problems without completely specifying the orderings between the actions in the plan. This property provides greater flexibility in executing plans; hence making the partial order planners a preferred choice over other planning methodologies. However, in order to find partially ordered plans, partial order planners perform a search in plan space rather than in space of world states and an uninformed search in plan space leads to poor efficiency. In this thesis, I discuss applying a reinforcement learning method, called First-visit Monte Carlo method, to partial order planning in order to design agents which do not need any training data or heuristics but are still able to make informed decisions in plan space based on experience. Communicating effectively with the agent is crucial in reinforcement learning. I address how this task was accomplished in plan space and the results from an evaluation of a blocks world test bed.
Subject
- Library of Congress Subject Headings: Reinforcement learning (Machine learning)
- Library of Congress Subject Headings: Intelligent agents (Computer software)
- Library of Congress Subject Headings: Artificial intelligence.
- Keyword: artificial intelligence
- Keyword: reinforcement learning
- Keyword: partial order planning
Collection
-
Name: UNT Theses and DissertationsCode: UNTETD
Institution
-
Name: UNT LibrariesCode: UNT
Rights
- Rights Access: unt
- Rights License: copyright
- Rights Holder: Ceylan, Hakan
- Rights Statement: Copyright is held by the author, unless otherwise noted. All rights reserved.
Resource Type
- Thesis or Dissertation
Format
- Text
Identifier
- OCLC: 70890296
- Archival Resource Key: ark:/67531/metadc5232
Degree
- Degree Name: Master of Science
- Degree Level: Master's
- Degree Discipline: Computer Science
- Academic Department: Department of Computer Science and Engineering
- Degree Grantor: University of North Texas