Show simple item record

dc.contributor.authorKim, Beomjoon
dc.contributor.authorKaelbling, Leslie P
dc.contributor.authorLozano-Pérez, Tomás
dc.date.accessioned2021-03-02T19:31:01Z
dc.date.available2021-03-02T19:31:01Z
dc.date.issued2019-07
dc.identifier.issn2374-3468
dc.identifier.issn2159-5399
dc.identifier.urihttps://hdl.handle.net/1721.1/130053
dc.description.abstractWe 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.sponsorshipNSF (Grants 1523767 and 1723381)en_US
dc.description.sponsorshipAFOSR (Grant FA9550-17-1-0165)en_US
dc.description.sponsorshipONR (Grant N00014-18-1-2847)en_US
dc.publisherAssociation for the Advancement of Artificial Intelligence (AAAI)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1609/aaai.v33i01.33018017en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceMIT web domainen_US
dc.titleAdversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experienceen_US
dc.typeArticleen_US
dc.identifier.citationKim, 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 Intelligenceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.relation.journalProceedings of the AAAI Conference on Artificial Intelligenceen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.date.submission2020-12-22T19:22:46Z
mit.journal.volume33en_US
mit.journal.issue1en_US
mit.licenseOPEN_ACCESS_POLICY
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record