{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T05:31:17Z","timestamp":1775194277559,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["61977019"],"award-info":[{"award-number":["61977019"]}],"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":["U1813206"],"award-info":[{"award-number":["U1813206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"crossref","award":["JCYJ20220818102415033"],"award-info":[{"award-number":["JCYJ20220818102415033"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"crossref","award":["JSGG20201103093802006"],"award-info":[{"award-number":["JSGG20201103093802006"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tii.2023.3336225","type":"journal-article","created":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T20:19:09Z","timestamp":1703189949000},"page":"5794-5804","source":"Crossref","is-referenced-by-count":12,"title":["FHCPL: An Intelligent Fixed-Horizon Constrained Policy Learning System for Risk-Sensitive Industrial Scenario"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3429-5877","authenticated-orcid":false,"given":"Ke","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2902-7365","authenticated-orcid":false,"given":"Duantengchuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7890-9677","authenticated-orcid":false,"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7157-4402","authenticated-orcid":false,"given":"Shiyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2396-1704","authenticated-orcid":false,"given":"Xindong","family":"Wu","sequence":"additional","affiliation":[{"name":"Research Center for Knowledge Engineering at the Zhejiang Lab, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3094207"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3145567"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","article-title":"Model based reinforcement learning for atari","volume-title":"Proc. Int. Conf. Learn. Representations","author":"ukasz","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3125252"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3033324"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3007167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3168319"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50815-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3151464"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref13","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garca","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Schulman","year":"2015"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref17","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Achiam","year":"2017"},{"key":"ref18","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"ref20","first-page":"8103","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chow","year":"2018"},{"key":"ref21","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Thomas","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.37.3.474"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref24","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Achiam","year":"2019"},{"key":"ref25","first-page":"12535","article-title":"On-policy deep reinforcement learning for the average-reward criterion","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Zhang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5784"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref28","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref30","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2020"},{"key":"ref31","first-page":"11480","article-title":"CRPO: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Xu","year":"2021"},{"key":"ref32","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Kakade","year":"2002"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/436"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.32604\/csse.2022.022365"},{"issue":"2","key":"ref36","first-page":"393","article-title":"Big data service architecture: A survey","volume":"21","author":"Wang","year":"2020","journal-title":"J. Internet Technol."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3446342"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3966\/160792642020012101001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3385414"},{"issue":"4","key":"ref40","first-page":"1161","article-title":"Research on recurrent neural network based crack opening prediction of concrete dam","volume":"21","author":"Wang","year":"2020","journal-title":"J.Internet Technol."}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10492489\/10368334.pdf?arnumber=10368334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T20:05:55Z","timestamp":1712693155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10368334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tii.2023.3336225","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}