{"id":"https://openalex.org/W4225820449","doi":"https://doi.org/10.1109/cdc45484.2021.9683748","title":"Model-Based Actor-Critic with Chance Constraint for Stochastic System","display_name":"Model-Based Actor-Critic with Chance Constraint for Stochastic System","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4225820449","doi":"https://doi.org/10.1109/cdc45484.2021.9683748"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683748","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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/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, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, 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, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, 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, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, 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, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021699314","display_name":"Yuming Yin","orcid":"https://orcid.org/0000-0002-2854-921X"},"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":"Yuming Yin","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, 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/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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","Shanghai Qi Zhi Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]}]}],"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":1.0053,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80538418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4694","last_page":"4700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9916999936103821,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9717000126838684,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426275610923767},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7372606992721558},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.638712465763092},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6217972636222839},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6076974868774414},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5784358382225037},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.4728182554244995},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4313179850578308},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.4307363033294678},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41690120100975037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2740323543548584},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.16562947630882263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11591017246246338},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0799153745174408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426275610923767},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7372606992721558},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.638712465763092},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6217972636222839},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6076974868774414},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5784358382225037},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4728182554244995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4313179850578308},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4307363033294678},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41690120100975037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2740323543548584},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.16562947630882263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11591017246246338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0799153745174408},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683748","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1144593952","https://openalex.org/W1845972764","https://openalex.org/W1978956894","https://openalex.org/W2020426342","https://openalex.org/W2101075098","https://openalex.org/W2123871098","https://openalex.org/W2131116400","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2557055507","https://openalex.org/W2570494446","https://openalex.org/W2765395770","https://openalex.org/W2766447205","https://openalex.org/W2784465508","https://openalex.org/W2804791273","https://openalex.org/W2942608247","https://openalex.org/W2982316857","https://openalex.org/W2994712737","https://openalex.org/W3002044607","https://openalex.org/W3011338904","https://openalex.org/W3088218629","https://openalex.org/W3162902207","https://openalex.org/W4244288018","https://openalex.org/W4288020947","https://openalex.org/W4288363736","https://openalex.org/W4293545785","https://openalex.org/W4297801897","https://openalex.org/W4410033702","https://openalex.org/W6631627413","https://openalex.org/W6680657880","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6747790125","https://openalex.org/W6751725685","https://openalex.org/W6770744290","https://openalex.org/W6771280675","https://openalex.org/W6948184010"],"related_works":["https://openalex.org/W4254717236","https://openalex.org/W2377757044","https://openalex.org/W3160952126","https://openalex.org/W2320103255","https://openalex.org/W798918733","https://openalex.org/W4213167601","https://openalex.org/W2101287851","https://openalex.org/W163279402","https://openalex.org/W2403168774","https://openalex.org/W2119531745"],"abstract_inverted_index":{"Safety":[0],"is":[1,121],"essential":[2],"for":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"applied":[7],"in":[8,20],"real-world":[9],"situations.":[10],"Chance":[11],"constraints":[12],"are":[13,93],"suitable":[14],"to":[15,101,113],"represent":[16],"the":[17,81,87,103,108],"safety":[18,161],"requirements":[19],"stochastic":[21,125,165],"systems.":[22],"Previous":[23],"chance":[24,54,83],"constrained":[25,55,84],"RL":[26,148],"methods":[27,71],"usually":[28],"learn":[29,62],"an":[30],"either":[31],"conservative":[32,75],"or":[33],"unsafe":[34],"policy,":[35],"and":[36,65,90],"some":[37],"of":[38,110,119],"them":[39],"also":[40,151],"suffer":[41],"from":[42,69],"a":[43,52,63,74,124,139],"low":[44],"convergence":[45,104,143],"rate.":[46],"In":[47,99],"this":[48],"paper,":[49],"we":[50],"propose":[51],"model-based":[53],"actor-critic":[56],"(CCAC)":[57],"algorithm":[58],"which":[59],"can":[60],"efficiently":[61],"safe":[64,91],"non-conservative":[66],"policy.":[67],"Different":[68],"existing":[70],"that":[72,130],"optimize":[73],"lower":[76],"bound,":[77],"CCAC":[78,106,120,131],"directly":[79],"solves":[80],"original":[82],"problems,":[85],"where":[86],"objective":[88],"function":[89],"probability":[92],"simultaneously":[94],"optimized":[95],"with":[96,138,146],"adaptive":[97],"weights.":[98],"order":[100],"improve":[102],"rate,":[105],"utilizes":[107],"gradient":[109],"dynamic":[111],"model":[112,166],"accelerate":[114],"policy":[115],"optimization.":[116],"The":[117],"effectiveness":[118],"demonstrated":[122],"by":[123],"car-following":[126],"task.":[127],"Experiments":[128],"indicate":[129],"achieves":[132],"good":[133],"performance":[134],"while":[135],"guaranteeing":[136],"safety,":[137],"five":[140],"times":[141,154],"faster":[142],"rate":[144],"compared":[145],"model-free":[147],"methods.":[149],"It":[150],"has":[152],"100":[153],"higher":[155],"online":[156],"computation":[157],"efficiency":[158],"than":[159],"traditional":[160],"techniques":[162],"such":[163],"as":[164],"predictive":[167],"control.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
