{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T07:45:33Z","timestamp":1769067933846,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61303108"],"award-info":[{"award-number":["61303108"]}],"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":["61772355"],"award-info":[{"award-number":["61772355"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010023","name":"Natural Science Research of Jiangsu Higher Education Institutions of China","doi-asserted-by":"publisher","award":["17KJA520004"],"award-info":[{"award-number":["17KJA520004"]}],"id":[{"id":"10.13039\/501100010023","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Suzhou Key Industries Technological Innovation-Prospective Applied Research Project","award":["SYG201804"],"award-info":[{"award-number":["SYG201804"]}]},{"DOI":"10.13039\/501100007824","name":"Soochow University","doi-asserted-by":"publisher","award":["KJS1524"],"award-info":[{"award-number":["KJS1524"]}],"id":[{"id":"10.13039\/501100007824","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010023","name":"Natural Science Research of Jiangsu Higher Education Institutions of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010023","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2952651","type":"journal-article","created":{"date-parts":[[2019,11,11]],"date-time":"2019-11-11T17:54:40Z","timestamp":1573494880000},"page":"165007-165017","source":"Crossref","is-referenced-by-count":28,"title":["Safe Q-Learning Method Based on Constrained Markov Decision Processes"],"prefix":"10.1109","volume":"7","author":[{"given":"Yangyang","family":"Ge","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2226-2859","authenticated-orcid":false,"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghong","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"109","article-title":"Risk-sensitive Markov decision process with limited budget","volume":"1","author":"moreira","year":"2018","journal-title":"Proc IEEE Brazilian Conf Intelligent Systems (BRACIS)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487170"},{"key":"ref33","first-page":"1","article-title":"Safe exploration in finite Markov decision processes with Gaussian processes","author":"turchetta","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623497326629"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2011.2107533"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.06.018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1080.0324"},{"key":"ref35","article-title":"Scaling up robust MDPs by reinforcement learning","author":"tamar","year":"0","journal-title":"Comput Sci"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13823-7_31"},{"key":"ref10","first-page":"1","article-title":"Policy gradients with variance related risk criteria","volume":"1","author":"castro","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref40","first-page":"1","article-title":"A Lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2018.11.079"},{"key":"ref12","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-neuro-072116-031526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080685"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2849556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref17","first-page":"2915","article-title":"Near optimal behavior via approximate state abstraction","volume":"48","author":"abel","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref19","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"Comput Sci"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/17M1125698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67380-6_70"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2018.2842085"},{"key":"ref5","first-page":"5573","article-title":"Revisiting the arcade learning environment: Evaluation protocols and open problems for general agents","volume":"61","author":"machado","year":"2017","journal-title":"J Artif Intell Res"},{"key":"ref8","first-page":"1037","article-title":"Smart exploration in reinforcement learning using absolute temporal difference errors","author":"gehring","year":"2013","journal-title":"Proc Int Conf Auton Agents Multi-Agent Syst"},{"key":"ref7","author":"luenberger","year":"2013","journal-title":"Investment Science"},{"key":"ref2","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000039779.47329.3a"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11590-018-01380-y"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.019"},{"key":"ref45","author":"sun","year":"2010","journal-title":"Optimization Method"},{"key":"ref22","article-title":"Reinforcement learning for multi-objective and constrained Markov decision processes","author":"gattami","year":"2019","journal-title":"arXiv 1901 08978"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcta.2018.09.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01117"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/make1010002"},{"key":"ref23","first-page":"1431","article-title":"Action-constrained Markov decision processes with Kullback-Leibler cost","volume":"75","author":"bu\u0161i?","year":"2018","journal-title":"Proc 31st Conf on Learning Theory 75"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISITA.2008.4895657"},{"key":"ref26","first-page":"1","article-title":"Constrained cross-entropy method for safe reinforcement learning","author":"min","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-015-0187-9"},{"key":"ref25","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08895829.pdf?arnumber=8895829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:32:11Z","timestamp":1641987131000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8895829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2952651","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}