{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T09:26:33Z","timestamp":1780478793043,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["61703138"],"award-info":[{"award-number":["61703138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["CSC202106710026"],"award-info":[{"award-number":["CSC202106710026"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B200202224"],"award-info":[{"award-number":["B200202224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B200204036"],"award-info":[{"award-number":["B200204036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3410162","type":"journal-article","created":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T17:53:41Z","timestamp":1718214821000},"page":"4323-4340","source":"Crossref","is-referenced-by-count":12,"title":["Deep Reinforcement Learning With Multiple Unrelated Rewards for AGV Mapless Navigation"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4411-8935","authenticated-orcid":false,"given":"Boliang","family":"Cai","sequence":"first","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Hohai University, Changzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5788-6573","authenticated-orcid":false,"given":"Changyun","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Hohai University, Changzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8968-9902","authenticated-orcid":false,"given":"Ze","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Engineering, Cardiff University, Cardiff, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206184"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3184990"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3145693"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5220\/0009821603140323"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01367-5"},{"key":"ref10","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8997292"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574707004092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917719333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MLISE57402.2022.00038"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3124093"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2000.870304"},{"key":"ref21","first-page":"1","article-title":"Multiplicative controller fusion: A hybrid navigation strategy for deployment in unknown environments","volume-title":"Proc. IEEE Int. Conf. Intell. Robots Syst.","author":"Rana"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.917224"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2010.2045501"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574714000289"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISRIMT53730.2021.9597113"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10131"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-022-00088-3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3097345"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO49542.2019.8961491"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9327532"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011438"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2018.8604791"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929120"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SIU55565.2022.9864769"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE56824.2022.9995813"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2023.3340659"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161312"},{"key":"ref45","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sutton"},{"key":"ref46","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3369712"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069883"},{"key":"ref49","first-page":"1627","article-title":"Decoupled neural interfaces using synthetic gradients","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Jaderberg"},{"key":"ref50","article-title":"Solving continuous control via Q-learning","author":"Seyde","year":"2022","journal-title":"arXiv:2210.12566"},{"key":"ref51","article-title":"Constrained policy optimization via Bayesian world models","author":"As","year":"2022","journal-title":"arXiv:2201.09802"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"ref53","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref54","first-page":"8787","article-title":"Decoupling value and policy for generalization in reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Raileanu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611487"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10555525.pdf?arnumber=10555525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:47:10Z","timestamp":1740422830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10555525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3410162","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}