dc.contributor.author | Kim, Beomjoon | |
dc.contributor.author | Kaelbling, Leslie P | |
dc.contributor.author | Lozano-Pérez, Tomás | |
dc.date.accessioned | 2021-03-02T19:31:01Z | |
dc.date.available | 2021-03-02T19:31:01Z | |
dc.date.issued | 2019-07 | |
dc.identifier.issn | 2374-3468 | |
dc.identifier.issn | 2159-5399 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/130053 | |
dc.description.abstract | We propose an actor-critic algorithm that uses past planning experience to improve the efficiency of solving robot task-and-motion planning (TAMP) problems. TAMP planners search for goal-achieving sequences of high-level operator instances specified by both discrete and continuous parameters. Our algorithm learns a policy for selecting the continuous parameters during search, using a small training set generated from the search trees of previously solved instances. We also introduce a novel fixed-length vector representation for world states with varying numbers of objects with different shapes, based on a set of key robot configurations. We demonstrate experimentally that our method learns more efficiently from less data than standard reinforcementlearning approaches and that using a learned policy to guide a planner results in the improvement of planning efficiency. | en_US |
dc.description.sponsorship | NSF (Grants 1523767 and 1723381) | en_US |
dc.description.sponsorship | AFOSR (Grant FA9550-17-1-0165) | en_US |
dc.description.sponsorship | ONR (Grant N00014-18-1-2847) | en_US |
dc.publisher | Association for the Advancement of Artificial Intelligence (AAAI) | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1609/aaai.v33i01.33018017 | en_US |
dc.rights | Creative Commons Attribution-Noncommercial-Share Alike | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | en_US |
dc.source | MIT web domain | en_US |
dc.title | Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Kim, Beomjoon et al. "Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience." Proceedings of the AAAI Conference on Artificial Intelligence 33, 1 (July 2019): 8017-8024 © 2019 Association for the Advancement of Artificial Intelligence | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.relation.journal | Proceedings of the AAAI Conference on Artificial Intelligence | en_US |
dc.eprint.version | Author's final manuscript | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
dspace.date.submission | 2020-12-22T19:22:46Z | |
mit.journal.volume | 33 | en_US |
mit.journal.issue | 1 | en_US |
mit.license | OPEN_ACCESS_POLICY | |
mit.metadata.status | Complete | |