{"id":"https://openalex.org/W3164927689","doi":"https://doi.org/10.1109/tsp.2022.3158737","title":"Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning","display_name":"Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3164927689","doi":"https://doi.org/10.1109/tsp.2022.3158737","mag":"3164927689"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2022.3158737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2022.3158737","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.12545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027767633","display_name":"Chang Tian","orcid":"https://orcid.org/0000-0002-1895-1758"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Tian","raw_affiliation_strings":["State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1895-1758","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340369","display_name":"An Liu","orcid":"https://orcid.org/0000-0002-3943-5234"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An Liu","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hang Zhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-3943-5234","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hang Zhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001803242","display_name":"Guan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guan Huang","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hang Zhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hang Zhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108200040","display_name":"Wu Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Luo","raw_affiliation_strings":["State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2306,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89181277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"70","issue":null,"first_page":"1609","last_page":"1624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6946296691894531},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.5632986426353455},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.560793936252594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5221393704414368},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.5145113468170166},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4464859962463379},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33609098196029663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3227475583553314}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6946296691894531},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.5632986426353455},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.560793936252594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5221393704414368},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5145113468170166},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4464859962463379},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33609098196029663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3227475583553314},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsp.2022.3158737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2022.3158737","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2105.12545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12545","pdf_url":"https://arxiv.org/pdf/2105.12545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.12545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12545","pdf_url":"https://arxiv.org/pdf/2105.12545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G710882353","display_name":null,"funder_award_id":"62071416","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W79131877","https://openalex.org/W1518931405","https://openalex.org/W1577245107","https://openalex.org/W1845972764","https://openalex.org/W2036749237","https://openalex.org/W2071563913","https://openalex.org/W2105336508","https://openalex.org/W2121863487","https://openalex.org/W2151299863","https://openalex.org/W2155027007","https://openalex.org/W2164536085","https://openalex.org/W2257979135","https://openalex.org/W2593769694","https://openalex.org/W2736601468","https://openalex.org/W2784465508","https://openalex.org/W2784709112","https://openalex.org/W2804791273","https://openalex.org/W2822752092","https://openalex.org/W2913300629","https://openalex.org/W2962803570","https://openalex.org/W2963082979","https://openalex.org/W2964222567","https://openalex.org/W2970927156","https://openalex.org/W2970999177","https://openalex.org/W2977813751","https://openalex.org/W2981915592","https://openalex.org/W2990747716","https://openalex.org/W2993185773","https://openalex.org/W2994712737","https://openalex.org/W2997273686","https://openalex.org/W3008953696","https://openalex.org/W3024883403","https://openalex.org/W3080734044","https://openalex.org/W3082245592","https://openalex.org/W3094019951","https://openalex.org/W3094224934","https://openalex.org/W3101517963","https://openalex.org/W3102309758","https://openalex.org/W3116213608","https://openalex.org/W3128962298","https://openalex.org/W3162902207","https://openalex.org/W3210807411","https://openalex.org/W4206497039","https://openalex.org/W4214717370","https://openalex.org/W4235050391","https://openalex.org/W4287725923","https://openalex.org/W4288022843","https://openalex.org/W4288359387","https://openalex.org/W4293545785","https://openalex.org/W6675698164","https://openalex.org/W6683204974","https://openalex.org/W6737893269","https://openalex.org/W6738741286","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6747790125","https://openalex.org/W6751725685","https://openalex.org/W6758924645","https://openalex.org/W6762263229","https://openalex.org/W6767434776","https://openalex.org/W6767486501","https://openalex.org/W6769954528","https://openalex.org/W6771280675","https://openalex.org/W6771428195","https://openalex.org/W6771608210","https://openalex.org/W6772215039","https://openalex.org/W6774406872","https://openalex.org/W6780587392","https://openalex.org/W6782263831","https://openalex.org/W6785187516","https://openalex.org/W6785471904","https://openalex.org/W6803550857"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3153752017"],"abstract_inverted_index":{"Constrained":[0],"reinforcement":[1,8],"learning":[2],"(CRL),":[3],"also":[4],"termed":[5],"as":[6,46],"safe":[7],"learning,":[9,130],"is":[10,44,61],"a":[11,28,47,65,134,143],"promising":[12],"technique":[13],"enabling":[14],"the":[15,39,56,75,81,114,119,124,131,148],"deployment":[16],"of":[17,55,67,93,118,147],"RL":[18],"agent":[19],"in":[20,53,80,105],"real-world":[21,106],"systems.":[22],"In":[23,116],"this":[24],"paper,":[25],"we":[26],"propose":[27],"successive":[29],"convex":[30,68,85],"approximation":[31],"based":[32,62],"off-policy":[33,129],"optimization":[34,70],"(SCAOPO)":[35],"algorithm":[36],"to":[37,111,142],"solve":[38],"general":[40],"CRL":[41],"problem,":[42],"which":[43],"formulated":[45],"constrained":[48],"Markov":[49],"decision":[50],"process":[51],"(CMDP)":[52],"context":[54],"average":[57],"cost.":[58],"The":[59,88],"SCAOPO":[60,90,132],"on":[63],"solving":[64],"sequence":[66],"objective/feasibility":[69],"problems":[71],"obtained":[72],"by":[73,128],"replacing":[74],"objective":[76],"and":[77,123],"constraint":[78],"functions":[79],"original":[82,149],"problem":[83,150],"with":[84,133],"surrogate":[86],"functions.":[87],"proposed":[89],"enables":[91],"reuse":[92],"experiences":[94],"from":[95],"previous":[96],"updates,":[97],"thereby":[98],"significantly":[99],"reducing":[100],"implementation":[101],"cost":[102],"when":[103],"deployed":[104],"engineering":[107],"systems":[108],"that":[109],"need":[110],"online":[112],"learn":[113],"environment.":[115],"spite":[117],"time-varying":[120],"state":[121],"distribution":[122],"stochastic":[125],"bias":[126],"incurred":[127],"feasible":[135],"initial":[136],"point":[137,146],"can":[138],"still":[139],"provably":[140],"converge":[141],"Karush-Kuhn-Tucker":[144],"(KKT)":[145],"almost":[151],"surely.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}