{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:41:13Z","timestamp":1784205673247,"version":"3.55.0"},"reference-count":49,"publisher":"Informa UK Limited","issue":"23","funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2022YFB3302700"],"award-info":[{"award-number":["2022YFB3302700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51825502"],"award-info":[{"award-number":["51825502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2029"],"award-info":[{"award-number":["U21B2029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1080\/00207543.2024.2335663","type":"journal-article","created":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T16:39:02Z","timestamp":1711816742000},"page":"8260-8275","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":22,"title":["An efficient and adaptive design of reinforcement learning environment to solve job shop scheduling problem with soft actor-critic algorithm"],"prefix":"10.1080","volume":"62","author":[{"given":"Jinghua","family":"Si","sequence":"first","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3730-0360","authenticated-orcid":false,"given":"Xinyu","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peigen","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207548208947745"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.2354"},{"key":"e_1_3_3_4_1","unstructured":"Brockman Greg Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. \u201cOpenAI Gym.\u201d Preprint arXiv:1606.01540."},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3167380"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(97)00019-2"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109255"},{"key":"e_1_3_3_9_1","doi-asserted-by":"crossref","unstructured":"Gupta Jayesh K. Maxim Egorov and Mykel Kochenderfer. 2017. \u201cCooperative Multi-Agent Control Using Deep Reinforcement Learning.\u201d In Autonomous Agents and Multiagent Systems edited by Gita Sukthankar and Juan A. Rodriguez-Aguilar Lecture Notes in Computer Science 66\u201383. Cham: Springer International Publishing.","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"e_1_3_3_10_1","unstructured":"Haarnoja Tuomas Haoran Tang Pieter Abbeel and Sergey Levine. 2017. \u201cReinforcement Learning with Deep Energy-Based Policies.\u201d In Proceedings of the 34th International Conference on Machine Learning 1352\u20131361. Sydney NSW: PMLR."},{"key":"e_1_3_3_11_1","unstructured":"Haarnoja Tuomas Aurick Zhou Pieter Abbeel and Sergey Levine. 2018. \u201cSoft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.\u201d In Proceedings of the 35th International Conference on Machine Learning 1861\u20131870. Stockholm: PMLR."},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/Access.6287639"},{"key":"e_1_3_3_13_1","doi-asserted-by":"crossref","unstructured":"Henderson Peter Riashat Islam Philip Bachman Joelle Pineau Doina Precup and David Meger. 2018. \u201cDeep Reinforcement Learning That Matters.\u201d In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 32. Washington DC: AAAI Press.","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Holcomb Sean D. William K. Porter Shaun V. Ault Guifen Mao and Jin Wang. 2018. \u201cOverview on DeepMind and Its AlphaGo Zero AI.\u201d In Proceedings of the 2018 International Conference on Big Data and Education (ICBDE 18) 67\u201371. New York NY: Association for Computing Machinery.","DOI":"10.1145\/3206157.3206174"},{"key":"e_1_3_3_15_1","volume-title":"Dynamic Programming and Markov Processes","author":"Howard Ronald A.","year":"1960","unstructured":"Howard, Ronald A. 1960. \u201cDynamic Programming and Markov Processes. Oxford: John Wiley."},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109650"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2023.06.007"},{"key":"e_1_3_3_18_1","unstructured":"Konda Vijay and John Tsitsiklis. 1999. \u201cActor-Critic Algorithms.\u201d In Advances in Neural Information Processing Systems Vol. 12. Denver CO: MIT Press."},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2019.02.101"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117796"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3069184"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-022-2096-6"},{"key":"e_1_3_3_23_1","unstructured":"Lillicrap Timothy P. Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2019. \u201cContinuous Control with Deep Reinforcement Learning.\u201d Preprint arXiv:1509.02971."},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.9424"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2023.102605"},{"issue":"2023","key":"e_1_3_3_26_1","first-page":"127","article-title":"An Improved Genetic Algorithm with Modified Critical Path-Based Searching for Integrated Process Planning and Scheduling Problem Considering Automated Guided Vehicle Transportation Task","volume":"70","author":"Liu Qihao","year":"2024","unstructured":"Liu, Qihao, Cuiyu Wang, Xinyu Li, and Liang Gao. 2024. \u201cAn Improved Genetic Algorithm with Modified Critical Path-Based Searching for Integrated Process Planning and Scheduling Problem Considering Automated Guided Vehicle Transportation Task.\u201d Journal of Manufacturing Systems 70 (2023): 127\u2013136.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2023.9010015"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107489"},{"key":"e_1_3_3_29_1","doi-asserted-by":"crossref","unstructured":"Mordatch Igor and Pieter Abbeel. 2018. \u201cEmergence of Grounded Compositional Language in Multi-Agent Populations.\u201d In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 32. Washington DC: AAAI Press.","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.06.067"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2267693"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1870013"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2980305"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2140221"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.11.397"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2172472"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(93)90182-M"},{"key":"e_1_3_3_39_1","unstructured":"Terry J. Benjamin Black Nathaniel Grammel Mario Jayakumar Ananth Hari Ryan Sullivan and Luis S. Santos et\u00a0al. 2021. \u201cPettingZoo: Gym for Multi-Agent Reinforcement Learning.\u201d In Advances in Neural Information Processing Systems Vol. 34 15032\u201315043. Curran Associates Inc."},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2245918"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107969"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.23919\/CSMS.2021.0027"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.07.017"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.212"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117460"},{"key":"e_1_3_3_46_1","unstructured":"Zhang Cong Wen Song Zhiguang Cao Jie Zhang Puay Siew Tan and Xu Chi. 2020. \u201cLearning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning.\u201d In Advances in Neural Information Processing Systems Vol. 33 1621\u20131632. Curran Associates Inc."},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3271666"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3110242"},{"key":"e_1_3_3_49_1","doi-asserted-by":"crossref","unstructured":"Zheng Lianmin Jiacheng Yang Han Cai Weinan Zhang Jun Wang and Yong Yu. 2017. \u201cMAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence.\u201d Preprint arXiv:1712.00600.","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2020.05.163"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2024.2335663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T09:43:14Z","timestamp":1730972594000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2024.2335663"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,30]]},"references-count":49,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["10.1080\/00207543.2024.2335663"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2024.2335663","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,30]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tprs20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tprs20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-05-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}