{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:52:45Z","timestamp":1778172765155,"version":"3.51.4"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1565\/20"],"award-info":[{"award-number":["1565\/20"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/lra.2022.3229266","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T18:34:54Z","timestamp":1671042894000},"page":"576-583","source":"Crossref","is-referenced-by-count":15,"title":["Learning to Throw With a Handful of Samples Using Decision Transformers"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6655-1823","authenticated-orcid":false,"given":"Maxim","family":"Monastirsky","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7188-9201","authenticated-orcid":false,"given":"Osher","family":"Azulay","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3320-3897","authenticated-orcid":false,"given":"Avishai","family":"Sintov","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel"}]}],"member":"263","reference":[{"key":"ref31","first-page":"24631","article-title":"Prompting decision transformer for few-shot policy generalization","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref10","article-title":"Planar robot casting with real2sim2real self-supervised learning","author":"lim","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref12","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref15","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref16","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref18","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Hindsight experience replay","author":"andrychowicz","year":"0","journal-title":"Proc Adv Neural Inf Proc Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref28","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139530"},{"key":"ref27","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"janner","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s10514-012-9290-3","article-title":"Reinforcement learning to adjust parameterized motor primitives to new situations","volume":"33","author":"kober","year":"0","journal-title":"Auton Robots"},{"key":"ref8","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9773-y"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216746"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651142"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206046"},{"key":"ref21","first-page":"937","article-title":"Motion control of a ball throwing robot with a flexible robotic arm","volume":"7","author":"gai","year":"2013","journal-title":"Int J Comput Inf Eng"},{"key":"ref24","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","author":"parisotto","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref26","article-title":"Rapid task-solving in novel environments","author":"ritter","year":"2020"},{"key":"ref25","article-title":"Relational deep reinforcement learning","author":"zambaldi","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9990971\/09984828.pdf?arnumber=9984828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:24:47Z","timestamp":1673897087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9984828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":31,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3229266","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}