{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:34:17Z","timestamp":1772832857192,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcds.2023.3345539","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T19:58:20Z","timestamp":1703275100000},"page":"1327-1341","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical Multicontact Motion Planning of Hexapod Robots With Incremental Reinforcement Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7456-0962","authenticated-orcid":false,"given":"Kaiqiang","family":"Tang","sequence":"first","affiliation":[{"name":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9403-2449","authenticated-orcid":false,"given":"Huiqiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6589-4402","authenticated-orcid":false,"given":"Guizhou","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Process equipment and control engineering, School of Manufacturing Science and Engineering, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3031-0056","authenticated-orcid":false,"given":"Xinpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Process equipment and control engineering, School of Manufacturing Science and Engineering, Southwest University of Science and Technology, Mianyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3049848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3096935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363191"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TePRA.2015.7219685"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/tee.23206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989624"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3083594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2681181"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2422267"},{"key":"ref14","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3187186"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004272"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2023.3240758"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2718938"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092647"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979660"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/328"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3316637"},{"key":"ref24","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2017"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref26","article-title":"Capturability based analysis, optimization and control of 3D bipedal walking","author":"Caron","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3213773"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593888"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2912417"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989131"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2955701"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2798285"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555778"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3133610"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110040"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280907"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3164719"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3039859"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593722"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2021.3120628"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8793864"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561717"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972879"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3149602"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2023.108339"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.110001"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023552"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3055499"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911390"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-020-01262-5"},{"key":"ref52","article-title":"Model-free reinforcement learning for robust locomotion using trajectory optimization for exploration","author":"Bogdanovic","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2975428"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102857"},{"key":"ref55","first-page":"1","article-title":"Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"4","author":"Kalifou","year":"2019"},{"key":"ref56","first-page":"1","article-title":"Ess-InfoGAIL: Semi-supervised imitation learning from imbalanced demonstrations","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Fu","year":"2023"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10633860\/10372214.pdf?arnumber=10372214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:12:05Z","timestamp":1723525925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10372214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":56,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3345539","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}