{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:31:15Z","timestamp":1783438275679,"version":"3.54.6"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tnnls.2023.3247160","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T18:25:27Z","timestamp":1677781527000},"page":"11049-11063","source":"Crossref","is-referenced-by-count":15,"title":["Representation Learning and Reinforcement Learning for Dynamic Complex Motion Planning System"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8297-5949","authenticated-orcid":false,"given":"Chengmin","family":"Zhou","sequence":"first","affiliation":[{"name":"Machine Learning Group, School of Computing, University of Eastern Finland, Joensuu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4748-2882","authenticated-orcid":false,"given":"Bingding","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Big Data and Internet, Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9554-2827","authenticated-orcid":false,"given":"Pasi","family":"Fr\u00e4nti","sequence":"additional","affiliation":[{"name":"Machine Learning Group, School of Computing, University of Eastern Finland, Joensuu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980508"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1990.145.367"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2012.6232212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2011.01.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2018.8623233"},{"key":"ref10","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Wang"},{"key":"ref11","first-page":"2850","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","volume":"4","author":"Mnih"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460504"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01588-5"},{"key":"ref19","article-title":"Relational graph learning for crowd navigation","author":"Chen","year":"2019","journal-title":"arXiv:1909.13165"},{"key":"ref20","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref21","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR) Conf. Track","author":"Schaul"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3209154"},{"key":"ref23","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref25","first-page":"2171","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"3","author":"Haarnoja"},{"key":"ref26","first-page":"605","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn. (ICML)","volume":"1","author":"Silver"},{"key":"ref27","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Harutyunyan"},{"key":"ref28","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","volume":"3","author":"Schulman"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref30","first-page":"2587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"4","author":"Fujimoto"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref32","first-page":"2976","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"5","author":"Haarnoja"},{"key":"ref33","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv:1910.07207"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084685"},{"key":"ref35","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv:1910.07207"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref37","first-page":"177","article-title":"ClearPath: Highly parallel collision avoidance for multi-agent simulation","volume-title":"Proc. Comput. Animat. Conf.","author":"Guyy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32323-3_12"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","first-page":"1","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR) Conf. Track","author":"Lin"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3174051"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10623582\/10058085.pdf?arnumber=10058085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T01:51:32Z","timestamp":1733881892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10058085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":44,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3247160","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}