{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T19:05:40Z","timestamp":1762455940428,"version":"build-2065373602"},"reference-count":37,"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":["62376048","62406050"],"award-info":[{"award-number":["62376048","62406050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"crossref","award":["2025-BS-0225"],"award-info":[{"award-number":["2025-BS-0225"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Laboratory of Multi-Domain Data Collaborative Processing and Control Foundation of China","award":["MDPC-20240303"],"award-info":[{"award-number":["MDPC-20240303"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["3132025269"],"award-info":[{"award-number":["3132025269"]}],"id":[{"id":"10.13039\/501100012226","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.2025.3625392","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:07:54Z","timestamp":1761588474000},"page":"23164-23176","source":"Crossref","is-referenced-by-count":0,"title":["Safe Refined Oil Dispatching via Constrained Multiagent Reinforcement Learning With Hierarchical Action Spaces"],"prefix":"10.1109","volume":"22","author":[{"given":"Kun","family":"Tang","sequence":"first","affiliation":[{"name":"College of Information Science and Technology, Dalian Maritime University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9157-6050","authenticated-orcid":false,"given":"Chengwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Dalian Maritime University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanting","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Dalian Maritime University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Li","sequence":"additional","affiliation":[{"name":"SINOPEC Dalian Research Institute of Petroleum and Petrochemicals Company Ltd., Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3249-8459","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Dalian Maritime University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2868-0186","authenticated-orcid":false,"given":"Dou","family":"An","sequence":"additional","affiliation":[{"name":"Department of Automation Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-2665","authenticated-orcid":false,"given":"Furui","family":"Zhan","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Dalian Maritime University, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.resourpol.2022.102689"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.esr.2025.101685"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2024.115907"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2024.108771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1987549"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2017.09.012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2018.05.103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2025.135275"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2022.117605"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2023.137409"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2023.138916"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121511"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.36.1.92"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2013.04.034"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2021.102223"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3544223"},{"issue":"4","key":"ref17","doi-asserted-by":"crossref","first-page":"2243","DOI":"10.3390\/app15042243","article-title":"Attention transfer reinforcement learning for test case prioritization in continuous integration","volume":"15","author":"Su","year":"2025","journal-title":"Appl. Sci."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3591311"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2025.105265","article-title":"Is cooperative always better? multi-agent reinforcement learning with explicit neighborhood backtracking for network-wide traffic signal control","volume":"179","author":"Ren","year":"2025","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.122023","article-title":"Integrated heterogeneous graph and reinforcement learning enabled efficient scheduling for surface Mount technology workshop","volume":"708","author":"Zhang","year":"2025","journal-title":"Inf. Sci."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-024-04970-x"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2023.106432","article-title":"Automatic design of constructive heuristics for a reconfigurable distributed flowshop group scheduling problem","volume":"161","author":"Zhang","year":"2024","journal-title":"Comput. Oper. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.7931"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2025.122117","article-title":"Finite-time safe reinforcement learning control of multi-player nonzero-sum game for quadcopter systems","volume":"712","author":"Tan","year":"2025","journal-title":"Inf. Sci."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3516494"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3577269"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0308997"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1088\/2631-8695\/add643"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3557472"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3374894"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/inte.20.4.74"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref33","first-page":"291","article-title":"Piecewise linear dynamic programming for constrained POMDPs","volume-title":"Proc. AAAI","author":"Isom"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref35","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref36","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","author":"Kuba","year":"2021","journal-title":"arXiv:2109.11251"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022602019183"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11216362.pdf?arnumber=11216362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:55:53Z","timestamp":1762455353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11216362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3625392","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"type":"print","value":"1545-5955"},{"type":"electronic","value":"1558-3783"}],"subject":[],"published":{"date-parts":[[2025]]}}}