Sidekick agents for sequential planning problems
Thesis (Ph. D.)--Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2013.
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | eng |
Published: |
Massachusetts Institute of Technology
2014
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/84892 |
_version_ | 1811083435335221248 |
---|---|
author | Macindoe, Owen |
author2 | Leslie Pack Kaelbling and Tomás Lozano-Pérez. |
author_facet | Leslie Pack Kaelbling and Tomás Lozano-Pérez. Macindoe, Owen |
author_sort | Macindoe, Owen |
collection | MIT |
description | Thesis (Ph. D.)--Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2013. |
first_indexed | 2024-09-23T12:33:01Z |
format | Thesis |
id | mit-1721.1/84892 |
institution | Massachusetts Institute of Technology |
language | eng |
last_indexed | 2024-09-23T12:33:01Z |
publishDate | 2014 |
publisher | Massachusetts Institute of Technology |
record_format | dspace |
spelling | mit-1721.1/848922019-04-11T10:56:35Z Sidekick agents for sequential planning problems Macindoe, Owen Leslie Pack Kaelbling and Tomás Lozano-Pérez. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis (Ph. D.)--Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2013. Cataloged from PDF version of thesis. Includes bibliographical references (pages 127-131). Effective Al sidekicks must solve the interlinked problems of understanding what their human collaborator's intentions are and planning actions to support them. This thesis explores a range of approximate but tractable approaches to planning for AI sidekicks based on decision-theoretic methods that reason about how the sidekick's actions will effect their beliefs about unobservable states of the world, including their collaborator's intentions. In doing so we extend an existing body of work on decision-theoretic models of assistance to support information gathering and communication actions. We also apply Monte Carlo tree search methods for partially observable domains to the problem and introduce an ensemble-based parallelization strategy. These planning techniques are demonstrated across a range of video game domains. by Owen Macindoe. Ph.D. 2014-02-10T16:59:23Z 2014-02-10T16:59:23Z 2013 Thesis http://hdl.handle.net/1721.1/84892 868823103 eng M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 131 pages application/pdf Massachusetts Institute of Technology |
spellingShingle | Electrical Engineering and Computer Science. Macindoe, Owen Sidekick agents for sequential planning problems |
title | Sidekick agents for sequential planning problems |
title_full | Sidekick agents for sequential planning problems |
title_fullStr | Sidekick agents for sequential planning problems |
title_full_unstemmed | Sidekick agents for sequential planning problems |
title_short | Sidekick agents for sequential planning problems |
title_sort | sidekick agents for sequential planning problems |
topic | Electrical Engineering and Computer Science. |
url | http://hdl.handle.net/1721.1/84892 |
work_keys_str_mv | AT macindoeowen sidekickagentsforsequentialplanningproblems |