{"id":"https://openalex.org/W3203497287","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534349","title":"Hierarchical Reinforcement Learning-Based Policy Switching Towards Multi-Scenarios Autonomous Driving","display_name":"Hierarchical Reinforcement Learning-Based Policy Switching Towards Multi-Scenarios Autonomous Driving","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3203497287","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534349","mag":"3203497287"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5090856768","display_name":"Youtian Guo","orcid":"https://orcid.org/0000-0002-0979-9344"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Youtian Guo","raw_affiliation_strings":["School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736381","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0002-8278-7083"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395785","display_name":"Junjie Wang","orcid":"https://orcid.org/0000-0001-9869-7085"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wang","raw_affiliation_strings":["School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376038","display_name":"Shasha Liu","orcid":"https://orcid.org/0009-0006-0287-8986"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shasha Liu","raw_affiliation_strings":["School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artifical Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090856768"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.2237,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83499862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.998199999332428,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9363971948623657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7333446145057678},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6157963275909424},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5021896362304688},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.5000960826873779},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45434707403182983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4254138469696045},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18601083755493164},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08015856146812439}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9363971948623657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333446145057678},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6157963275909424},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5021896362304688},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.5000960826873779},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45434707403182983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4254138469696045},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18601083755493164},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08015856146812439},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1488730473","https://openalex.org/W1771410628","https://openalex.org/W1969074599","https://openalex.org/W2109910161","https://openalex.org/W2119717200","https://openalex.org/W2133853511","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2187089797","https://openalex.org/W2417280899","https://openalex.org/W2736601468","https://openalex.org/W2771734675","https://openalex.org/W2803281228","https://openalex.org/W2898691144","https://openalex.org/W2907385442","https://openalex.org/W2939569248","https://openalex.org/W2950614095","https://openalex.org/W2962782357","https://openalex.org/W2962894046","https://openalex.org/W2963262099","https://openalex.org/W2963430540","https://openalex.org/W2963438456","https://openalex.org/W2964227312","https://openalex.org/W2968983352","https://openalex.org/W2970787054","https://openalex.org/W2977843878","https://openalex.org/W2978967214","https://openalex.org/W2991115325","https://openalex.org/W2996726407","https://openalex.org/W3007474893","https://openalex.org/W3034445502","https://openalex.org/W3040033967","https://openalex.org/W3093963693","https://openalex.org/W3095440204","https://openalex.org/W3119981760","https://openalex.org/W6629152578","https://openalex.org/W6638018090","https://openalex.org/W6683443546","https://openalex.org/W6683821272","https://openalex.org/W6703271639","https://openalex.org/W6727349600","https://openalex.org/W6746404916","https://openalex.org/W6752089545","https://openalex.org/W6756319914","https://openalex.org/W6776812925","https://openalex.org/W6784178060"],"related_works":["https://openalex.org/W1543048115","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,33,67],"has":[2],"gained":[3],"a":[4,37,64,71,86],"lot":[5],"of":[6,13,23,48,103],"attention":[7],"and":[8,50,106],"applications":[9,26],"in":[10,16,52,119],"the":[11,20,31,45,53,101,116,120],"field":[12],"autonomous":[14,55],"driving":[15,25,39,56,79],"recent":[17],"years.":[18],"However,":[19],"actual":[21],"scenarios":[22],"automatic":[24],"are":[27],"often":[28],"diverse,":[29],"so":[30],"reinforcement":[32,66],"algorithm":[34],"using":[35],"only":[36],"single":[38,104],"strategy":[40],"is":[41],"difficult":[42],"to":[43,69],"meet":[44],"multiple":[46],"requirements":[47],"efficiency":[49],"safety":[51],"multi-scenarios":[54],"task.":[57],"To":[58],"solve":[59],"this":[60,112],"challenge,":[61],"we":[62,114],"propose":[63],"hierarchical":[65],"structure":[68],"learn":[70],"unified":[72],"top-level":[73],"switching":[74,108],"master":[75],"policy":[76,105],"between":[77],"different":[78],"styles":[80],"policies.":[81],"The":[82],"whole":[83],"framework":[84],"uses":[85],"bottom-up":[87],"training":[88],"manner":[89],"with":[90],"diverse":[91],"reward":[92],"function":[93],"designing.":[94],"Through":[95],"experimental":[96],"comparison,":[97],"our":[98],"method":[99],"exceeds":[100],"performance":[102],"rule-based":[107],"strategy.":[109],"Based":[110],"on":[111],"framework,":[113],"won":[115],"first":[117],"place":[118],"DAI":[121],"2020":[122],"Autonomous":[123],"Driving":[124],"Workshop":[125],"single-agent":[126],"track":[127],"competition.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}