{"id":"https://openalex.org/W3215986979","doi":"https://doi.org/10.1109/crc52766.2021.9620159","title":"A Survey of Research on Stability Guarantee of Reinforcement Learning Automatic Control Problem","display_name":"A Survey of Research on Stability Guarantee of Reinforcement Learning Automatic Control Problem","publication_year":2021,"publication_date":"2021-10-09","ids":{"openalex":"https://openalex.org/W3215986979","doi":"https://doi.org/10.1109/crc52766.2021.9620159","mag":"3215986979"},"language":"en","primary_location":{"id":"doi:10.1109/crc52766.2021.9620159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc52766.2021.9620159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th International Conference on Control, Robotics and Cybernetics (CRC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088821715","display_name":"Quan Fu Gan","orcid":"https://orcid.org/0000-0001-6699-1618"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Gan","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030271803","display_name":"Fengge Wu","orcid":"https://orcid.org/0000-0002-1958-8321"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengge Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069584904","display_name":"Junsuo Zhao","orcid":"https://orcid.org/0000-0001-8950-4157"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsuo Zhao","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088821715"],"corresponding_institution_ids":["https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.1373,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.47231442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"249"},"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":0.9905999898910522,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.911928653717041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7010605335235596},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5945119261741638},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.593245267868042},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5930622816085815},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5884646773338318},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43041831254959106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.428615003824234},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.34737128019332886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.326795756816864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.911928653717041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010605335235596},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5945119261741638},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.593245267868042},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5930622816085815},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5884646773338318},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43041831254959106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.428615003824234},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.34737128019332886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.326795756816864},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/crc52766.2021.9620159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc52766.2021.9620159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th International Conference on Control, Robotics and Cybernetics (CRC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1502922572","https://openalex.org/W1771410628","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W2006859604","https://openalex.org/W2120034667","https://openalex.org/W2143277772","https://openalex.org/W2155511972","https://openalex.org/W2164479831","https://openalex.org/W2298163601","https://openalex.org/W2468321057","https://openalex.org/W2572949971","https://openalex.org/W2586823359","https://openalex.org/W2784465508","https://openalex.org/W2789826932","https://openalex.org/W2892521964","https://openalex.org/W2913300629","https://openalex.org/W2962775887","https://openalex.org/W2963175324","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2964337106","https://openalex.org/W2966735560","https://openalex.org/W2970795963","https://openalex.org/W2977676795","https://openalex.org/W2979251496","https://openalex.org/W2989090915","https://openalex.org/W2996196387","https://openalex.org/W3003648996","https://openalex.org/W3046925685","https://openalex.org/W3091691175","https://openalex.org/W3098713169","https://openalex.org/W3099442372","https://openalex.org/W3102238624","https://openalex.org/W3117881175","https://openalex.org/W3124229194","https://openalex.org/W3162902207","https://openalex.org/W4289709949","https://openalex.org/W4293275986","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4297799385","https://openalex.org/W6629804754","https://openalex.org/W6638018090","https://openalex.org/W6677959772","https://openalex.org/W6683149736","https://openalex.org/W6684037837","https://openalex.org/W6687063787","https://openalex.org/W6695920968","https://openalex.org/W6719477708","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6747790125","https://openalex.org/W6751535212","https://openalex.org/W6753691991","https://openalex.org/W6758924645","https://openalex.org/W6764988152","https://openalex.org/W6767277667","https://openalex.org/W6770686191","https://openalex.org/W6772100842","https://openalex.org/W6773859063"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,30,74],"has":[2],"achieved":[3],"numerous":[4],"theoretical":[5],"and":[6,38,68,89],"application":[7,26],"results":[8],"in":[9,20],"the":[10,15,25,29,41,50,62,73,85],"field":[11],"of":[12,17,28,40,44,91],"control,":[13],"but":[14],"exploration":[16],"dangerous":[18],"situations":[19,23],"many":[21],"practical":[22],"limits":[24],"scenarios":[27],"methods.":[31],"This":[32],"paper":[33],"makes":[34],"a":[35],"systematic":[36],"introduction":[37],"summary":[39],"safety":[42,54,67,80],"methods":[43,59,70],"reinforcement":[45],"learning.":[46],"It":[47],"sorts":[48],"out":[49],"ideas":[51],"for":[52],"solving":[53],"from":[55],"two":[56],"aspects:":[57],"model-based":[58],"which":[60,71],"use":[61],"model":[63],"knowledge":[64],"to":[65,78],"ensure":[66],"model-free":[69],"change":[72],"object":[75],"or":[76],"process":[77],"give":[79],"guarantees.":[81],"Finally,":[82],"we":[83],"discuss":[84],"future":[86],"research":[87],"directions":[88],"prospects":[90],"these":[92],"problems.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}