{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:48:28Z","timestamp":1784389708796,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1728412"],"award-info":[{"award-number":["1728412"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tro.2023.3286046","type":"journal-article","created":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T17:30:36Z","timestamp":1688664636000},"page":"3382-3401","source":"Crossref","is-referenced-by-count":42,"title":["Reinforcement Learning of CPG-Regulated Locomotion Controller for a Soft Snake Robot"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4373-1359","authenticated-orcid":false,"given":"Xuan","family":"Liu","sequence":"first","affiliation":[{"name":"Robotics Engineering Department, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3307-1273","authenticated-orcid":false,"given":"Cagdas D.","family":"Onal","sequence":"additional","affiliation":[{"name":"Robotics Engineering Department, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3147-6805","authenticated-orcid":false,"given":"Jie","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/aa644c"},{"key":"ref35","article-title":"Temporal abstraction in reinforcement learning","author":"precup","year":"2000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-009-0049-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793774"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-016-0373-9"},{"key":"ref36","article-title":"OpenAI baselines","author":"dhariwal","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/105971239900700202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.915426"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570574"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/1729881417723440"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.03.014"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2013.0001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2922493"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30353-1_31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2012.2237519"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref19","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3218167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-011-0432-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00319514"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340763"},{"key":"ref25","article-title":"Frequency responses of a neural oscillator","author":"matsuoka","year":"2013"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref42","article-title":"Twin delayed deep deterministic policy gradient-based intelligent computation offloading for IoT","author":"chen","year":"2022","journal-title":"Digit Commun Netw"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.01.005"},{"key":"ref22","first-page":"308","article-title":"The intrinsic factors in the act of progression in the mammal","volume":"84","author":"brown","year":"0","journal-title":"Proc Roy Soc B Biol Sci"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00449593"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2016.0041"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.599242"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2013.0011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-7194-9_49-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-014-0592-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884619"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.1998.tb09036.x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907084980"},{"key":"ref5","first-page":"623","article-title":"Reinforcement learning for CPG-driven biped robot","volume":"4","author":"mori","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref40","author":"choset","year":"2005","journal-title":"Principles of Robot Motion Theory Algorithms and Implementation"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8860\/10271771\/10175020-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10271771\/10175020.pdf?arnumber=10175020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:42:16Z","timestamp":1698086536000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10175020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":42,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tro.2023.3286046","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}