| dc.contributor |
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
|
| dc.contributor |
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
|
| dc.contributor |
Kaelbling, Leslie P |
|
| dc.contributor |
Lozano-Perez, Tomas |
|
| dc.creator |
Konidaris, George |
|
| dc.creator |
Kaelbling, Leslie P |
|
| dc.creator |
Lozano-Perez, Tomas |
|
| dc.date |
2018-06-22T18:13:03Z |
|
| dc.date |
2018-06-22T18:13:03Z |
|
| dc.date |
2015-07 |
|
| dc.date.accessioned |
2023-03-01T18:10:33Z |
|
| dc.date.available |
2023-03-01T18:10:33Z |
|
| dc.identifier |
978-1-57735-738-4 |
|
| dc.identifier |
http://hdl.handle.net/1721.1/116532 |
|
| dc.identifier |
Konidaris, George et al. "Symbol Acquisition for Probabilistic High-Level Planning" Proceedings of the Twenty Fourth International Joint Conference on Artificial Intelligence (IJCAI),Buenos Aires, Argentina, AAAI Press / International Joint Conferences on Artificial Intelligence, 2015. |
|
| dc.identifier |
https://orcid.org/0000-0001-6054-7145 |
|
| dc.identifier |
https://orcid.org/0000-0002-8657-2450 |
|
| dc.identifier.uri |
http://localhost:8080/xmlui/handle/CUHPOERS/279034 |
|
| dc.description |
We introduce a framework that enables an agent to autonomously learn its own symbolic representation of a low-level, continuous environment. Propositional symbols are formalized as names for probability distributions, providing a natural means of dealing with uncertain representations and probabilistic plans. We determine the symbols that are sufficient for computing the probability with which a plan will succeed, and demonstrate the acquisition of a symbolic representation in a computer game domain. |
|
| dc.description |
National Science Foundation (U.S.) (grant 1420927) |
|
| dc.description |
United States. Office of Naval Research (grant N00014-14-1-0486) |
|
| dc.description |
United States. Air Force. Office of Scientific Research (grant FA23861014135) |
|
| dc.description |
United States. Army Research Office (grant W911NF1410433) |
|
| dc.description |
MIT Intelligence Initiative |
|
| dc.format |
application/pdf |
|
| dc.language |
en_US |
|
| dc.publisher |
AAAI Press / International Joint Conferences on Artificial Intelligence |
|
| dc.relation |
http://dl.acm.org/citation.cfm?id=2832754 |
|
| dc.relation |
24th International Joint Conference on Artificial Intelligence (IJCAI 2015) |
|
| dc.rights |
Creative Commons Attribution-Noncommercial-Share Alike |
|
| dc.rights |
http://creativecommons.org/licenses/by-nc-sa/4.0/ |
|
| dc.source |
MIT Web Domain |
|
| dc.title |
Symbol acquisition for probabilistic high-level planning |
|
| dc.type |
Article |
|
| dc.type |
http://purl.org/eprint/type/ConferencePaper |
|