{"id":"https://openalex.org/W3133255192","doi":"https://doi.org/10.1109/iv48863.2021.9575205","title":"Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning","display_name":"Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3133255192","doi":"https://doi.org/10.1109/iv48863.2021.9575205","mag":"3133255192"},"language":"en","primary_location":{"id":"doi:10.1109/iv48863.2021.9575205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv48863.2021.9575205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.08539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007610450","display_name":"Baiyu Peng","orcid":"https://orcid.org/0000-0001-9346-1858"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baiyu Peng","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102128057","display_name":"Yao Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Mu","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082794136","display_name":"Yang Guan","orcid":"https://orcid.org/0000-0003-0689-0510"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guan","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,State Key Laboratory of Automotive Safety and Energy,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100611365","display_name":"Jianyu Chen","orcid":"https://orcid.org/0000-0002-1835-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Chen","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","Institute for Interdisciplinary Information Sciences, Tsinghua University Beijing China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University Beijing China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007610450"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6058,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70839859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9904999732971191,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9904999732971191,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9883999824523926,"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/T10524","display_name":"Traffic control and management","score":0.9837999939918518,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7396885752677917},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6260359883308411},{"id":"https://openalex.org/keywords/lagrangian","display_name":"Lagrangian","score":0.5583013296127319},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5461016297340393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5302837491035461},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5140977501869202},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4999876022338867},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47954627871513367},{"id":"https://openalex.org/keywords/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.45081740617752075},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.44979217648506165},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4455462694168091},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.41925734281539917},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3408028483390808},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.25129425525665283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22334879636764526},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.15978708863258362},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13581150770187378},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08886018395423889}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7396885752677917},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6260359883308411},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.5583013296127319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5461016297340393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5302837491035461},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5140977501869202},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4999876022338867},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47954627871513367},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.45081740617752075},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.44979217648506165},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4455462694168091},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.41925734281539917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3408028483390808},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25129425525665283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22334879636764526},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.15978708863258362},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13581150770187378},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08886018395423889},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iv48863.2021.9575205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv48863.2021.9575205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.08539","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08539","pdf_url":"https://arxiv.org/pdf/2102.08539","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"},{"id":"mag:3133255192","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.08539","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.08539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.08539","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.08539","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08539","pdf_url":"https://arxiv.org/pdf/2102.08539","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3011866667","display_name":null,"funder_award_id":"2019YFE0100200","funder_id":"https://openalex.org/F4320335830","funder_display_name":"International Science and Technology Cooperation Programme"}],"funders":[{"id":"https://openalex.org/F4320335830","display_name":"International Science and Technology Cooperation Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2045798132","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2296319761","https://openalex.org/W2345459662","https://openalex.org/W2557055507","https://openalex.org/W2616964725","https://openalex.org/W2761873684","https://openalex.org/W2785389871","https://openalex.org/W2798391154","https://openalex.org/W2804791273","https://openalex.org/W2919115771","https://openalex.org/W2941428926","https://openalex.org/W2945137235","https://openalex.org/W2963082979","https://openalex.org/W2966850587","https://openalex.org/W2982316857","https://openalex.org/W3002044607","https://openalex.org/W3011338904","https://openalex.org/W3041244724","https://openalex.org/W3088218629","https://openalex.org/W3134476446","https://openalex.org/W4250589301","https://openalex.org/W4410033702","https://openalex.org/W6639175102","https://openalex.org/W6680657880","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6747473740","https://openalex.org/W6748519856","https://openalex.org/W6751725685","https://openalex.org/W6771280675","https://openalex.org/W6780587392","https://openalex.org/W6786446748","https://openalex.org/W6788400625"],"related_works":["https://openalex.org/W3195860693","https://openalex.org/W3116213608","https://openalex.org/W2508795747","https://openalex.org/W3049652862","https://openalex.org/W2081945146","https://openalex.org/W2994442364","https://openalex.org/W73727125","https://openalex.org/W3180158572","https://openalex.org/W2912849082","https://openalex.org/W2967560250","https://openalex.org/W2912832158","https://openalex.org/W2937687161","https://openalex.org/W2901175338","https://openalex.org/W2800791762","https://openalex.org/W3124030782","https://openalex.org/W3119933750","https://openalex.org/W2896448969","https://openalex.org/W3201995110","https://openalex.org/W3011326522","https://openalex.org/W2280099822"],"abstract_inverted_index":{"Safety":[0],"is":[1,20,141,153],"essential":[2],"for":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"applied":[7],"in":[8,143],"real-world":[9],"tasks":[10],"like":[11,36],"autonomous":[12],"driving.":[13],"Imposing":[14],"chance":[15,32],"constraints":[16],"(or":[17],"probabilistic":[18],"constraints)":[19],"a":[21,70,133,144,164],"suitable":[22],"way":[23],"to":[24,86,99,109,118,127,147,155],"enhance":[25],"RL":[26,34],"safety":[27,162],"under":[28],"model":[29],"uncertainty.":[30],"Existing":[31],"constrained":[33],"methods":[35,39,43,67,80,95],"the":[37,41,87,100,104,113,120,129,137],"penalty":[38,79],"and":[40,68,93,115,158],"Lagrangian":[42,73,94],"either":[44],"exhibit":[45],"periodic":[46],"oscillations":[47,157],"or":[48,52],"learn":[49],"an":[50,123],"over-conservative":[51],"unsafe":[53],"policy.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,107],"address":[59],"these":[60,65],"shortcomings":[61],"by":[62,163],"elegantly":[63],"combining":[64],"two":[66],"propose":[69,108],"separated":[71],"proportional-integral":[72],"(SPIL)":[74],"algorithm.":[75],"We":[76],"first":[77],"rewrite":[78],"as":[81,96],"optimizing":[82,97],"safe":[83],"probability":[84],"according":[85,98],"proportional":[88],"value":[89,102,131],"of":[90,103,139],"constraint":[91],"violation,":[92],"integral":[101,114,124,130],"violation.":[105],"Then":[106],"add":[110],"up":[111],"both":[112],"proportion":[116],"values":[117],"optimize":[119],"policy,":[121],"with":[122],"separation":[125],"technique":[126],"limit":[128],"within":[132],"reasonable":[134],"range.":[135],"Besides,":[136],"gradient":[138],"policy":[140],"computed":[142],"model-based":[145],"paradigm":[146],"accelerate":[148],"training.":[149],"The":[150],"proposed":[151],"method":[152],"proved":[154],"reduce":[156],"conservatism":[159],"while":[160],"ensuring":[161],"car-following":[165],"experiment.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}