{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:34:36Z","timestamp":1750224876144,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["62062033"],"award-info":[{"award-number":["62062033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20232BAB202018"],"award-info":[{"award-number":["20232BAB202018"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Systems Journal"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/jsyst.2023.3301032","type":"journal-article","created":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T17:38:12Z","timestamp":1692121092000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Large Vehicle Scheduling Based on Uncertainty Weighting Harmonic Twin-Critic Network"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7269-4484","authenticated-orcid":false,"given":"Xiaohui","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4604-1740","authenticated-orcid":false,"given":"Kaiming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9681-8119","authenticated-orcid":false,"given":"Jiahao","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467096"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3096226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3098779"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00202"},{"key":"ref30","first-page":"2613","article-title":"Double Q-learning","author":"hasselt","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 23 24th Annu Conf Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330724"},{"key":"ref10","first-page":"11319","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"wu","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3166446"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/inte.2020.1047"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC52481.2021.9702196"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2019.2962159"},{"key":"ref19","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","author":"agarwal","year":"0","journal-title":"Proc 37th Int Conf Mach Learn Virtual Event"},{"key":"ref18","first-page":"1785","article-title":"Better exploration with optimistic actor critic","author":"ciosek","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 32 Annu Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.093"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3075501"},{"key":"ref26","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume":"139","author":"liu","year":"0","journal-title":"Proc 38th Int Conf Mach Learn Virtual Event"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3138941"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/276"},{"key":"ref22","first-page":"1","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","author":"lan","year":"0","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref21","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","author":"pan","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3152162"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/186"},{"key":"ref29","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"0","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref7","first-page":"2021","article-title":"TAAC: Temporally abstract actor-critic for continuous control","author":"yu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 34 Annu Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Proc 35th Int Conf Mach Learn Stockholmsmässan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3172242"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3151651"},{"key":"ref6","first-page":"4018","article-title":"Diversity actor-critic: Sample-aware entropy regularization for sample-efficient exploration","author":"han","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref5","first-page":"980","article-title":"Low-precision reinforcement learning: Running soft actor-critic in half precision","author":"bj\u00f6rck","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"}],"container-title":["IEEE Systems Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4267003\/4357939\/10219435.pdf?arnumber=10219435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T01:59:47Z","timestamp":1702432787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10219435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/jsyst.2023.3301032","relation":{},"ISSN":["1932-8184","1937-9234","2373-7816"],"issn-type":[{"type":"print","value":"1932-8184"},{"type":"electronic","value":"1937-9234"},{"type":"electronic","value":"2373-7816"}],"subject":[],"published":{"date-parts":[[2023]]}}}