{"id":"https://openalex.org/W3115648115","doi":"https://doi.org/10.1109/itsc45102.2020.9294262","title":"Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization","display_name":"Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization","publication_year":2020,"publication_date":"2020-09-20","ids":{"openalex":"https://openalex.org/W3115648115","doi":"https://doi.org/10.1109/itsc45102.2020.9294262","mag":"3115648115"},"language":"en","primary_location":{"id":"doi:10.1109/itsc45102.2020.9294262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","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/A5109870380","display_name":"Lu Wen","orcid":"https://orcid.org/0009-0006-5558-2820"},"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"]},{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Lu Wen","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China","University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"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":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011184498","display_name":"Shaobing Xu","orcid":"https://orcid.org/0000-0002-4127-2411"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaobing Xu","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019025642","display_name":"Huei Peng","orcid":"https://orcid.org/0000-0002-1844-3163"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huei Peng","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109870380"],"corresponding_institution_ids":["https://openalex.org/I27837315","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.8958,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96043356,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10524","display_name":"Traffic control and management","score":0.9919999837875366,"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":0.8897314071655273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6498874425888062},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5180490016937256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438706398010254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17388629913330078},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06992518901824951}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8897314071655273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498874425888062},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5180490016937256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438706398010254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17388629913330078},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06992518901824951}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc45102.2020.9294262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1564754565","https://openalex.org/W1771410628","https://openalex.org/W1840625103","https://openalex.org/W1845972764","https://openalex.org/W1965878388","https://openalex.org/W2101075098","https://openalex.org/W2121863487","https://openalex.org/W2156737235","https://openalex.org/W2162849300","https://openalex.org/W2165150801","https://openalex.org/W2169619645","https://openalex.org/W2173248099","https://openalex.org/W2606508169","https://openalex.org/W2736601468","https://openalex.org/W2752924917","https://openalex.org/W2897614258","https://openalex.org/W2962803570","https://openalex.org/W2962977206","https://openalex.org/W2963575966","https://openalex.org/W2963864421","https://openalex.org/W2964108826","https://openalex.org/W2971510799","https://openalex.org/W3002044607","https://openalex.org/W3007923353","https://openalex.org/W3015082424","https://openalex.org/W3104013016","https://openalex.org/W3106238320","https://openalex.org/W4293545785","https://openalex.org/W4302570325","https://openalex.org/W4394661925","https://openalex.org/W6639175102","https://openalex.org/W6684921986","https://openalex.org/W6685043521","https://openalex.org/W6736482081","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6756925679","https://openalex.org/W6775294054"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,73,134],"(RL)":[2],"is":[3,101],"attracting":[4],"increasing":[5],"interests":[6],"in":[7,75],"autonomous":[8,61,143],"driving":[9,62],"due":[10],"to":[11,14,28,70,82,103,127],"its":[12],"potential":[13],"solve":[15],"complex":[16],"classification":[17],"and":[18,38,89,135],"control":[19],"problems.":[20],"However,":[21],"existing":[22],"RL":[23,51],"algorithms":[24],"are":[25,36,80,125],"rarely":[26],"applied":[27],"real":[29],"vehicles":[30,144],"for":[31,59,142],"two":[32,60,140],"predominant":[33],"problems:":[34],"behaviors":[35],"unexplainable,":[37],"they":[39],"cannot":[40],"guarantee":[41],"safety":[42,119,149],"under":[43],"new":[44],"scenarios.":[45],"This":[46],"paper":[47],"presents":[48],"a":[49,71,90,97],"safe":[50],"algorithm,":[52],"called":[53],"Parallel":[54],"Constrained":[55],"Policy":[56],"Optimization":[57],"(PCPO),":[58],"tasks.":[63],"PCPO":[64],"extends":[65],"today\u2019s":[66],"common":[67],"actor-critic":[68],"architecture":[69],"three-component":[72],"framework,":[74],"which":[76,132],"three":[77],"neural":[78],"networks":[79],"used":[81],"approximate":[83],"the":[84,110,116],"policy":[85],"function,":[86,94],"value":[87],"function":[88],"newly":[91],"added":[92,102],"risk":[93],"respectively.":[95],"Meanwhile,":[96],"trust":[98],"region":[99],"constraint":[100],"allow":[104],"large":[105],"update":[106],"steps":[107],"without":[108],"breaking":[109],"monotonic":[111],"improvement":[112],"condition.":[113],"To":[114],"ensure":[115,148],"feasibility":[117],"of":[118,139],"constrained":[120],"problems,":[121],"synchronized":[122],"parallel":[123],"learners":[124],"employed":[126],"explore":[128],"different":[129],"state":[130],"spaces,":[131],"accelerates":[133],"policy-update.":[136],"The":[137],"simulations":[138],"scenarios":[141],"confirm":[145],"we":[146],"can":[147],"while":[150],"achieving":[151],"fast":[152],"learning.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}