Symbol acquisition for task-level planning
We consider the problem of how to plan efficiently in low-level, continuous state spaces with temporally abstract actions (or skills), by constructing abstract representations of the problem suitable for task-level planning.The central question this effort poses is which abstract representations are...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
American Association for the Advancement of Science (AAAS)
2014
|
| Online Access: | http://hdl.handle.net/1721.1/90275 https://orcid.org/0000-0002-8657-2450 https://orcid.org/0000-0001-6054-7145 |
| _version_ | 1826210811324923904 |
|---|---|
| author | Konidaris, George Kaelbling, Leslie P. Lozano-Perez, Tomas |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Konidaris, George Kaelbling, Leslie P. Lozano-Perez, Tomas |
| author_sort | Konidaris, George |
| collection | MIT |
| description | We consider the problem of how to plan efficiently in low-level, continuous state spaces with temporally abstract actions (or skills), by constructing abstract representations of the problem suitable for task-level planning.The central question this effort poses is which abstract representations are required to express and evaluate plans composed of sequences of skills. We show that classifiers can be used as a symbolic representation system, and that the ability to represent the preconditions and effects of an agent's skills is both necessary and sufficient for task-level planning.The resulting representations allow a reinforcement learning agent to acquire a symbolic representation appropriate for planning from experience. |
| first_indexed | 2024-09-23T14:56:07Z |
| format | Article |
| id | mit-1721.1/90275 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:56:07Z |
| publishDate | 2014 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | dspace |
| spelling | mit-1721.1/902752022-10-01T23:25:49Z Symbol acquisition for task-level planning Konidaris, George Kaelbling, Leslie P. Lozano-Perez, Tomas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Konidaris, George Kaelbling, Leslie P. Lozano-Perez, Tomas We consider the problem of how to plan efficiently in low-level, continuous state spaces with temporally abstract actions (or skills), by constructing abstract representations of the problem suitable for task-level planning.The central question this effort poses is which abstract representations are required to express and evaluate plans composed of sequences of skills. We show that classifiers can be used as a symbolic representation system, and that the ability to represent the preconditions and effects of an agent's skills is both necessary and sufficient for task-level planning.The resulting representations allow a reinforcement learning agent to acquire a symbolic representation appropriate for planning from experience. 2014-09-22T19:21:38Z 2014-09-22T19:21:38Z 2013-06 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/90275 KONIDARIS, G.; KAELBLING, L.; LOZANO-PEREZ, T. Symbol Acquisition for Task-Level Planning. AAAI Workshops, North America, jun. 2013. https://orcid.org/0000-0002-8657-2450 https://orcid.org/0000-0001-6054-7145 en_US http://www.aaai.org/ocs/index.php/WS/AAAIW13/paper/view/7147 Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf American Association for the Advancement of Science (AAAS) MIT web domain |
| spellingShingle | Konidaris, George Kaelbling, Leslie P. Lozano-Perez, Tomas Symbol acquisition for task-level planning |
| title | Symbol acquisition for task-level planning |
| title_full | Symbol acquisition for task-level planning |
| title_fullStr | Symbol acquisition for task-level planning |
| title_full_unstemmed | Symbol acquisition for task-level planning |
| title_short | Symbol acquisition for task-level planning |
| title_sort | symbol acquisition for task level planning |
| url | http://hdl.handle.net/1721.1/90275 https://orcid.org/0000-0002-8657-2450 https://orcid.org/0000-0001-6054-7145 |
| work_keys_str_mv | AT konidarisgeorge symbolacquisitionfortasklevelplanning AT kaelblinglesliep symbolacquisitionfortasklevelplanning AT lozanopereztomas symbolacquisitionfortasklevelplanning |