{"id":"https://openalex.org/W2985692297","doi":"https://doi.org/10.1109/access.2019.2952651","title":"Safe Q-Learning Method Based on Constrained Markov Decision Processes","display_name":"Safe Q-Learning Method Based on Constrained Markov Decision Processes","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2985692297","doi":"https://doi.org/10.1109/access.2019.2952651","mag":"2985692297"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2952651","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2952651","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08895829.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08895829.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004357380","display_name":"Yangyang Ge","orcid":"https://orcid.org/0000-0002-1185-9684"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Ge","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074124642","display_name":"Fei Zhu","orcid":"https://orcid.org/0000-0002-2226-2859"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Zhu","raw_affiliation_strings":["Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou, China","School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2226-2859","affiliations":[{"raw_affiliation_string":"Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012325495","display_name":"Xinghong Ling","orcid":"https://orcid.org/0009-0009-0031-0942"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghong Ling","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414574","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-8710-1810"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.4635,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89590581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"165007","last_page":"165017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7012383937835693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6662900447845459},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6622800230979919},{"id":"https://openalex.org/keywords/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.641593873500824},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6326900720596313},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6291824579238892},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.5196443796157837},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4980792999267578},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4585423767566681},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41675931215286255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22221729159355164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2161705195903778},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15981322526931763}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7012383937835693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662900447845459},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6622800230979919},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.641593873500824},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6326900720596313},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6291824579238892},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.5196443796157837},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4980792999267578},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4585423767566681},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41675931215286255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22221729159355164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2161705195903778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15981322526931763},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2952651","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2952651","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08895829.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7024bea66b944b3fb1827b7643fdf8b1","is_oa":true,"landing_page_url":"https://doaj.org/article/7024bea66b944b3fb1827b7643fdf8b1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 165007-165017 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2952651","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2952651","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08895829.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1055180593","display_name":null,"funder_award_id":"61772355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G21622510","display_name":null,"funder_award_id":"61303108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3051587060","display_name":null,"funder_award_id":"17KJA520004","funder_id":"https://openalex.org/F4320335440","funder_display_name":"Natural Science Research of Jiangsu Higher Education Institutions of China"},{"id":"https://openalex.org/G7370257148","display_name":null,"funder_award_id":"KJS1524","funder_id":"https://openalex.org/F4320324720","funder_display_name":"Soochow University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324720","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null},{"id":"https://openalex.org/F4320335440","display_name":"Natural Science Research of Jiangsu Higher Education Institutions of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2985692297.pdf","grobid_xml":"https://content.openalex.org/works/W2985692297.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1518931405","https://openalex.org/W1845972764","https://openalex.org/W1991359458","https://openalex.org/W2013406658","https://openalex.org/W2070570138","https://openalex.org/W2090324313","https://openalex.org/W2100993276","https://openalex.org/W2121863487","https://openalex.org/W2133632477","https://openalex.org/W2134491302","https://openalex.org/W2143277772","https://openalex.org/W2144357336","https://openalex.org/W2145339207","https://openalex.org/W2162849300","https://openalex.org/W2169619645","https://openalex.org/W2197493596","https://openalex.org/W2201581102","https://openalex.org/W2288565641","https://openalex.org/W2427917354","https://openalex.org/W2462102501","https://openalex.org/W2468354762","https://openalex.org/W2519236774","https://openalex.org/W2582888895","https://openalex.org/W2583993537","https://openalex.org/W2600886565","https://openalex.org/W2739573821","https://openalex.org/W2740384884","https://openalex.org/W2755596511","https://openalex.org/W2756144809","https://openalex.org/W2782594573","https://openalex.org/W2789489570","https://openalex.org/W2806604749","https://openalex.org/W2808709600","https://openalex.org/W2809317103","https://openalex.org/W2883020154","https://openalex.org/W2889696653","https://openalex.org/W2892151043","https://openalex.org/W2903203445","https://openalex.org/W2911951998","https://openalex.org/W2913022628","https://openalex.org/W2962803570","https://openalex.org/W2963312138","https://openalex.org/W2963403143","https://openalex.org/W2963477884","https://openalex.org/W2963958573","https://openalex.org/W2964108826","https://openalex.org/W2964340170","https://openalex.org/W3099442372","https://openalex.org/W3100944043","https://openalex.org/W3105293562","https://openalex.org/W4214717370","https://openalex.org/W4293545785","https://openalex.org/W4294562617","https://openalex.org/W6685043521","https://openalex.org/W6687681856","https://openalex.org/W6687820959","https://openalex.org/W6717915398","https://openalex.org/W6719911377","https://openalex.org/W6737893269","https://openalex.org/W6744128076","https://openalex.org/W6751535212","https://openalex.org/W6758797660","https://openalex.org/W6765793075"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W2807018115","https://openalex.org/W4388236136","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W4200250224","https://openalex.org/W2970347269"],"abstract_inverted_index":{"The":[0,236],"application":[1],"of":[2,12,29,52,126,132,140,190,212,224,241],"reinforcement":[3],"learning":[4],"in":[5,130,204],"industrial":[6],"fields":[7],"makes":[8],"the":[9,13,22,26,30,34,43,53,56,74,99,108,113,118,124,128,133,137,141,146,151,154,163,167,175,191,197,205,210,220,225,232,239,242],"safety":[10,35,94,119,152],"problem":[11],"agent":[14,31,44,142],"a":[15,63,81],"research":[16],"hotspot.":[17],"Traditional":[18],"methods":[19,54,170],"mainly":[20],"alter":[21],"objective":[23],"function":[24],"and":[25,222],"exploration":[27],"process":[28,125],"to":[32,72,98,145,162,174,182,195,230],"address":[33],"problem.":[36],"Those":[37],"methods,":[38],"however,":[39],"can":[40,201],"hardly":[41],"prevent":[42],"from":[45],"falling":[46],"into":[47],"dangerous":[48],"states":[49],"because":[50],"most":[51,65],"ignore":[55],"damage":[57],"caused":[58],"by":[59,159],"unsafe":[60],"states.":[61],"As":[62],"result,":[64],"solutions":[66],"are":[67,171],"not":[68,172,217],"satisfactory.":[69],"In":[70],"order":[71],"solve":[73,196],"aforementioned":[75],"problem,":[76],"we":[77,187],"come":[78],"forward":[79],"with":[80],"safe":[82,147,176],"Q-learning":[83,104,177],"method":[84,194],"that":[85,107,117,149,200],"is":[86,121,143],"based":[87,208],"on":[88,209],"constrained":[89],"Markov":[90],"decision":[91],"processes,":[92],"adding":[93],"constraints":[95,160],"as":[96,179],"prerequisites":[97],"model,":[100],"which":[101,216],"improves":[102,219],"standard":[103],"algorithm":[105,110],"so":[106],"proposed":[109],"seeks":[111],"for":[112],"optimal":[114,134,185,198,234],"solution":[115,129,169],"ensuring":[116],"premise":[120,211],"satisfied.":[122],"During":[123],"finding":[127],"form":[131],"state-action":[135],"value,":[136],"feasible":[138,155],"space":[139,148,156],"limited":[144],"guarantees":[150,229],"via":[153],"being":[157],"filtered":[158],"added":[161],"action":[164,199],"space.":[165],"Because":[166],"traditional":[168],"applicable":[173],"model":[178],"they":[180],"tend":[181],"obtain":[183,231],"local":[184],"solution,":[186],"take":[188],"advantage":[189],"Lagrange":[192],"multiplier":[193],"be":[202],"performed":[203],"current":[206],"state":[207],"linearizing":[213],"constraint":[214],"functions,":[215],"only":[218],"efficiency":[221],"accuracy":[223],"algorithm,":[226],"but":[227],"also":[228],"global":[233],"solution.":[235],"experiments":[237],"verify":[238],"effectiveness":[240],"algorithm.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}