{"id":"https://openalex.org/W6888435287","doi":"https://doi.org/10.21227/gr5v-xg04","title":"Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving","display_name":"Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving","publication_year":2025,"publication_date":"2025-01-21","ids":{"openalex":"https://openalex.org/W6888435287","doi":"https://doi.org/10.21227/gr5v-xg04"},"language":"en","primary_location":{"id":"doi:10.21227/gr5v-xg04","is_oa":true,"landing_page_url":"https://doi.org/10.21227/gr5v-xg04","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/gr5v-xg04","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jin, Guizhe","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jin, Guizhe","raw_affiliation_strings":["School of Automotive Studies, Tongji University"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Zhuoren","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhuoren","raw_affiliation_strings":["School of Automotive Studies, Tongji University"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo, Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo, Leng","raw_affiliation_strings":["School of Automotive Studies, Tongji University"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han, Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Wei","raw_affiliation_strings":["School of Automotive Studies, Tongji University"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiong, Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong, Lu","raw_affiliation_strings":["School of Automotive Studies, Tongji University"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sun, Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Sun, Chen","raw_affiliation_strings":["Department of Data and Systems Engineering, University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Data and Systems Engineering, University of Hong Kong","institution_ids":["https://openalex.org/I889458895","https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8623999953269958},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.6367999911308289},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43380001187324524},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.424699991941452},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.30329999327659607}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8623999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506999731063843},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.6367999911308289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29679998755455017},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/gr5v-xg04","is_oa":true,"landing_page_url":"https://doi.org/10.21227/gr5v-xg04","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.21227/gr5v-xg04","is_oa":true,"landing_page_url":"https://doi.org/10.21227/gr5v-xg04","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8022887110710144}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"shown":[4],"excellent":[5],"performance":[6,102],"in":[7,20,33,42,69,89,119],"solving":[8],"decision-making":[9],"and":[10,46,75,96,114],"control":[11],"problems":[12],"of":[13,91,103],"autonomous":[14,64,87],"driving,":[15],"which":[16],"is":[17,26],"increasingly":[18],"applied":[19],"diverse":[21],"driving":[22,25,88,92,105],"scenarios.":[23],"However,":[24],"a":[27,51],"multi-attribute":[28],"problem,":[29],"leading":[30],"to":[31],"challenges":[32],"achieving":[34],"multi-objective":[35,62,85],"compatibility":[36],"for":[37,61],"current":[38],"RL":[39],"methods,":[40],"especially":[41],"both":[43,70],"policy":[44,47],"execution":[45],"iteration.":[48],"We":[49],"propose":[50],"Multi-objective":[52],"Ensemble-Critic":[53],"reinforcement":[54],"learning":[55],"method":[56,82],"with":[57],"Hybrid":[58],"Parametrized":[59],"Action":[60],"compatible":[63,86],"driving.":[65],"The":[66,111],"experimental":[67],"results":[68],"the":[71,76,100,104],"simulated":[72],"traffic":[73],"environment":[74],"HighD":[77],"dataset":[78],"demonstrate":[79],"that":[80],"our":[81],"can":[83],"achieve":[84],"terms":[90],"efficiency,":[93],"action":[94],"consistency,":[95],"safety.":[97],"It":[98],"enhances":[99],"general":[101],"while":[106],"significantly":[107],"increasing":[108],"training":[109,113],"efficiency.":[110],"detailed":[112],"testing":[115],"data":[116],"are":[117],"presented":[118],"this":[120],"dataset.":[121]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}