{"id":"https://openalex.org/W4387914680","doi":"https://doi.org/10.1109/mnet.005.2300020","title":"A Novel Generalized Meta Hierarchical Reinforcement Learning Method for Autonomous Vehicles","display_name":"A Novel Generalized Meta Hierarchical Reinforcement Learning Method for Autonomous Vehicles","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4387914680","doi":"https://doi.org/10.1109/mnet.005.2300020"},"language":"en","primary_location":{"id":"doi:10.1109/mnet.005.2300020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mnet.005.2300020","pdf_url":null,"source":{"id":"https://openalex.org/S186584794","display_name":"IEEE Network","issn_l":"0890-8044","issn":["0890-8044","1558-156X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Network","raw_type":"journal-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/A5102785196","display_name":"Longquan Chen","orcid":"https://orcid.org/0000-0002-4340-1360"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longquan Chen","raw_affiliation_strings":["Shenzhen University,China","Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693517","display_name":"Ying He","orcid":"https://orcid.org/0000-0003-1733-9791"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying He","raw_affiliation_strings":["Shenzhen University,China","Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073490832","display_name":"Weike Pan","orcid":"https://orcid.org/0000-0001-6326-9531"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weike Pan","raw_affiliation_strings":["Shenzhen University,China","Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"F. Richard Yu","raw_affiliation_strings":["Shenzhen University,China","Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633973","display_name":"Zhong Ming","orcid":"https://orcid.org/0000-0001-9310-3460"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Ming","raw_affiliation_strings":["Shenzhen University,China","Shenzhen University, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University,China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102785196"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":1.4011,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85256801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"37","issue":"4","first_page":"230","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9846000075340271,"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9222439527511597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.769569993019104},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6474249362945557},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.615799069404602},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.613400936126709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5615987181663513},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5409716963768005},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.519170880317688},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.43904706835746765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3336276710033417},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10657384991645813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0963769257068634},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.077044278383255}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9222439527511597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769569993019104},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6474249362945557},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.615799069404602},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.613400936126709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615987181663513},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5409716963768005},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.519170880317688},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.43904706835746765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3336276710033417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10657384991645813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0963769257068634},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.077044278383255},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mnet.005.2300020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mnet.005.2300020","pdf_url":null,"source":{"id":"https://openalex.org/S186584794","display_name":"IEEE Network","issn_l":"0890-8044","issn":["0890-8044","1558-156X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Network","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2109910161","https://openalex.org/W2342840547","https://openalex.org/W2736601468","https://openalex.org/W2963161674","https://openalex.org/W2963262099","https://openalex.org/W2966033451","https://openalex.org/W2966461828","https://openalex.org/W3002044607","https://openalex.org/W3175558129","https://openalex.org/W3194149012","https://openalex.org/W3205321526","https://openalex.org/W4213286046","https://openalex.org/W4294646197","https://openalex.org/W4297822034","https://openalex.org/W6703271639","https://openalex.org/W6704559304","https://openalex.org/W6739436346","https://openalex.org/W6741002519","https://openalex.org/W6744935223","https://openalex.org/W6750254146"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W3130669838","https://openalex.org/W2785397462","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W4283332751","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Despite":[0],"the":[1,51,69,73,86,90,100],"recent":[2],"successes":[3],"of":[4,72,94,102],"deep":[5],"reinforcement":[6,44,127],"learning,":[7,48],"there":[8],"still":[9],"remain":[10],"challenges":[11],"for":[12,41,60],"its":[13],"real-world":[14],"applications,":[15],"such":[16],"as":[17],"autonomous":[18,61,106,131],"vehicles.":[19,132],"There":[20],"are":[21,93],"two":[22],"main":[23],"issues:":[24],"sample":[25,52,120],"inefficiency":[26],"and":[27,54,67,89,104,110,122],"poor":[28],"generalization.":[29],"In":[30,76],"this":[31],"article,":[32],"we":[33,78],"propose":[34],"a":[35,56,80],"novel":[36],"method,":[37],"called":[38],"MHRL-I,":[39,84],"short":[40],"meta":[42],"hierarchical":[43],"learning":[45,128],"with":[46,125],"imitation":[47],"to":[49],"improve":[50],"efficiency":[53,121],"learn":[55],"more":[57,108],"generalized":[58],"model":[59],"vehicles":[62],"by":[63],"reusing":[64],"low-level":[65,91],"policies":[66,92],"reducing":[68],"action":[70],"space":[71],"high-level":[74,87],"policy.":[75],"addition,":[77],"design":[79],"new":[81],"mechanism":[82],"in":[83,130],"where":[85],"policy":[88],"different":[95],"timescales,":[96],"which":[97],"can":[98,117],"increase":[99],"speed":[101],"convergence":[103],"make":[105],"driving":[107],"stable":[109],"comfortable.":[111],"Simulation":[112],"results":[113],"show":[114],"that":[115],"MHRL-I":[116],"have":[118],"better":[119],"generalization":[123],"compared":[124],"other":[126],"methods":[129]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}