{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T19:14:01Z","timestamp":1771960441933,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3040896","type":"journal-article","created":{"date-parts":[[2020,11,27]],"date-time":"2020-11-27T20:23:51Z","timestamp":1606508631000},"page":"217541-217553","source":"Crossref","is-referenced-by-count":20,"title":["Overcoming Obstacles With a Reconfigurable Robot Using Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4577-3990","authenticated-orcid":false,"given":"Liran","family":"Yehezkel","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7717-7259","authenticated-orcid":false,"given":"Sigal","family":"Berman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3106-1861","authenticated-orcid":false,"given":"David","family":"Zarrouk","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","year":"2020","journal-title":"Web Link Address"},{"key":"ref38","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref33","author":"shimkin","year":"2020","journal-title":"Reinforcement Learning—Basic Algorithms Learning in Complex Systems Spring 2011 Lecture Notes"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989186"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2966414"},{"key":"ref37","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref35","article-title":"Learning image-conditioned dynamics models for control of under-actuated legged millirobots","author":"nagabandi","year":"2017","journal-title":"arXiv 1711 05253"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794351"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942981"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/11840817_87"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.02.004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986838"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s18082585"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5402\/2013\/849606"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2805165"},{"key":"ref16","year":"2020","journal-title":"YouTube Video"},{"key":"ref17","author":"sutton","year":"2012","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03194-1_2"},{"key":"ref19","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906069150"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354561"},{"key":"ref6","article-title":"X-RHex: A highly mobile hexapedal robot for sensorimotor tasks","author":"galloway","year":"2010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630551"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364902021010837"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2010.5626034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2382981"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1250609"},{"key":"ref20","article-title":"Reinforcement learning on self-reconfigurable modular robots","author":"kirkner","year":"2007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468643"},{"key":"ref21","first-page":"3003","article-title":"Quadruped robot obstacle negotiation via reinforcement learning","author":"lee","year":"2006","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IRIS.2017.8250126"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/RoMoCo.2019.8787360"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCO.2016.7727034"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09272763.pdf?arnumber=9272763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:14Z","timestamp":1639770914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9272763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3040896","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}