Using Reinforcement Learning in Partial Order Plan Space

Use of this thesis is restricted to the UNT Community. Off-campus users must log in to read.

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 ... continued below

Creation Information

Ceylan, Hakan May 2006.

Context

This thesis is part of the collection entitled: UNT Theses and Dissertations and was provided by UNT Libraries to Digital Library, a digital repository hosted by the UNT Libraries. It has been viewed 84 times , with 5 in the last month . More information about this thesis can be viewed below.

Who

People and organizations associated with either the creation of this thesis or its content.

Author

Chair

Committee Members

Publisher

Rights Holder

For guidance see Citations, Rights, Re-Use.

  • Ceylan, Hakan

Provided By

UNT Libraries

Library facilities at the University of North Texas function as the nerve center for teaching and academic research. In addition to a major collection of electronic journals, books and databases, five campus facilities house just under six million cataloged holdings, including books, periodicals, maps, documents, microforms, audiovisual materials, music scores, full-text journals and books. A branch library is located at the University of North Texas Dallas Campus.

Contact Us

What

Descriptive information to help identify this thesis. Follow the links below to find similar items on the Digital Library.

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.

Language

Identifier

Unique identifying numbers for this thesis in the Digital Library or other systems.

Collections

This thesis is part of the following collection of related materials.

UNT Theses and Dissertations

Theses and dissertations represent a wealth of scholarly and artistic content created by masters and doctoral students in the degree-seeking process. Some ETDs in this collection are restricted to use by the UNT community.

What responsibilities do I have when using this thesis?

When

Dates and time periods associated with this thesis.

Creation Date

  • May 2006

Added to The UNT Digital Library

  • May 5, 2008, 2:14 p.m.

Description Last Updated

  • May 6, 2014, 4:20 p.m.

Usage Statistics

When was this thesis last used?

Yesterday: 0
Past 30 days: 5
Total Uses: 84

Interact With This Thesis

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

Citations, Rights, Re-Use

Ceylan, Hakan. Using Reinforcement Learning in Partial Order Plan Space, thesis, May 2006; Denton, Texas. (digital.library.unt.edu/ark:/67531/metadc5232/: accessed April 30, 2017), University of North Texas Libraries, Digital Library, digital.library.unt.edu; .