{"id":"https://openalex.org/W4391769306","doi":"https://doi.org/10.1109/itsc57777.2023.10422026","title":"MEERL: Maximum Experience Entropy Reinforcement Learning Method for Navigation and Control of Automated Vehicles","display_name":"MEERL: Maximum Experience Entropy Reinforcement Learning Method for Navigation and Control of Automated Vehicles","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4391769306","doi":"https://doi.org/10.1109/itsc57777.2023.10422026"},"language":"en","primary_location":{"id":"doi:10.1109/itsc57777.2023.10422026","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itsc57777.2023.10422026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017388383","display_name":"Xin Bi","orcid":"https://orcid.org/0000-0002-2645-1112"},"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":"Xin Bi","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067209720","display_name":"Caien Weng","orcid":"https://orcid.org/0000-0003-3167-633X"},"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":"Caien Weng","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073334903","display_name":"Panpan Tong","orcid":"https://orcid.org/0000-0002-0027-4437"},"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":"Panpan Tong","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024008212","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0003-4227-1741"},"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 Zhang","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078343111","display_name":"Zhichao Li","orcid":"https://orcid.org/0000-0001-6803-6876"},"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":"Zhichao Li","raw_affiliation_strings":["School of Automotive Studies, Tongji University,Shanghai,China,201804"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University,Shanghai,China,201804","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"8","issue":null,"first_page":"1103","last_page":"1109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9674999713897705,"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":0.9674999713897705,"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":0.9656000137329102,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9002000093460083,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8036375641822815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6468180418014526},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6130263805389404},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.522614061832428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.506817638874054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38024258613586426}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8036375641822815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6468180418014526},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6130263805389404},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.522614061832428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506817638874054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38024258613586426},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc57777.2023.10422026","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/itsc57777.2023.10422026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4266936530","display_name":null,"funder_award_id":"2021-YF08-00140-GX","funder_id":"https://openalex.org/F4320326670","funder_display_name":"Chengdu Science and Technology Bureau"},{"id":"https://openalex.org/G5853038666","display_name":null,"funder_award_id":"2021YFB2501201,2018AAA0102801","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320326670","display_name":"Chengdu Science and Technology Bureau","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1959608418","https://openalex.org/W2032558547","https://openalex.org/W2098774185","https://openalex.org/W2119717200","https://openalex.org/W2155007355","https://openalex.org/W2188365844","https://openalex.org/W2511837229","https://openalex.org/W2736601468","https://openalex.org/W2765302304","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2787800669","https://openalex.org/W2803308811","https://openalex.org/W2898757087","https://openalex.org/W2902298341","https://openalex.org/W2946531308","https://openalex.org/W2951507724","https://openalex.org/W2953318193","https://openalex.org/W4214717370","https://openalex.org/W4239125046","https://openalex.org/W4241996101","https://openalex.org/W4287907550","https://openalex.org/W4298876402","https://openalex.org/W4299828299","https://openalex.org/W4302570325","https://openalex.org/W6640963894","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6683300800","https://openalex.org/W6684205842","https://openalex.org/W6687045409","https://openalex.org/W6725708968","https://openalex.org/W6734206676","https://openalex.org/W6734517396","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748594472","https://openalex.org/W6751629939","https://openalex.org/W6755625160","https://openalex.org/W6757058172","https://openalex.org/W6763153117","https://openalex.org/W6771788113"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"The":[0],"maximum":[1,28,56,61,97,133],"entropy":[2,29,57,63,99,106,134],"reinforcement":[3,12,30,58,64,135],"learning":[4,31,65,136],"is":[5,86],"one":[6],"of":[7,107],"the":[8,27,44,48,74,81,105,108,131],"promising":[9],"methods":[10],"for":[11,22],"learning,":[13,59],"which":[14,85],"has":[15],"been":[16],"widely":[17],"studied":[18],"in":[19],"automated":[20],"vehicles":[21],"navigation":[23,113],"and":[24,47,100,115,128],"control.":[25],"However,":[26],"method":[32,72,123],"still":[33],"suffers":[34],"from":[35,80],"sample":[36,69,126],"inefficiency.":[37],"Besides,":[38],"it":[39],"fails":[40],"to":[41,67,76,103],"distinguish":[42],"between":[43],"behaviour":[45],"policy":[46,83],"evaluation":[49],"policy.":[50,110],"This":[51],"article":[52],"presents":[53],"an":[54],"improved":[55],"namely":[60],"experience":[62],"(MEERL),":[66],"reduce":[68],"complexity.":[70],"Our":[71],"drives":[73],"agent":[75],"select":[77],"actions":[78],"far":[79],"historical":[82,89,101,109],"distribution,":[84],"estimated":[87],"by":[88],"trajectories.":[90],"To":[91],"curtail":[92],"repeated":[93],"trails,":[94],"we":[95,119],"introduce":[96],"cross":[98],"resampling":[102],"maximize":[104],"In":[111],"a":[112],"task":[114],"Mujoco":[116],"control":[117],"tasks,":[118],"demonstrate":[120],"that":[121],"our":[122],"enjoys":[124],"better":[125],"efficiency":[127],"performance":[129],"than":[130],"state-of-the-art":[132],"method.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}