{"id":"https://openalex.org/W4405305769","doi":"https://doi.org/10.1109/indin58382.2024.10774316","title":"Value Conditional State Entropy Reinforcement Learning for Autonomous Driving Decision Making","display_name":"Value Conditional State Entropy Reinforcement Learning for Autonomous Driving Decision Making","publication_year":2024,"publication_date":"2024-08-18","ids":{"openalex":"https://openalex.org/W4405305769","doi":"https://doi.org/10.1109/indin58382.2024.10774316"},"language":"en","primary_location":{"id":"doi:10.1109/indin58382.2024.10774316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin58382.2024.10774316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)","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/A5111053442","display_name":"Yiyi Han","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":"Yiyi Han","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066128993","display_name":"Lulu Guo","orcid":"https://orcid.org/0000-0003-2285-2469"},"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":"Lulu Guo","raw_affiliation_strings":["Tongji University,Department of Control Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Control Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100761000","display_name":"Chen Hong","orcid":"https://orcid.org/0000-0002-1376-9789"},"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":"Hong Chen","raw_affiliation_strings":["Tongji University, School of Automotive Studies,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, School of Automotive Studies,Shanghai,China","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":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9661999940872192,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9661999940872192,"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":0.9470000267028809,"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":0.8016787767410278},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.6712251901626587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5700337886810303},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5472398400306702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4690723121166229},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3889278173446655},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3203481137752533},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06935396790504456}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8016787767410278},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.6712251901626587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5700337886810303},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5472398400306702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690723121166229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3889278173446655},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3203481137752533},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06935396790504456},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/indin58382.2024.10774316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin58382.2024.10774316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1637889902","display_name":null,"funder_award_id":"62203334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3576156782","display_name":null,"funder_award_id":"22YF1451300","funder_id":"https://openalex.org/F4320327803","funder_display_name":"Shanghai Rising-Star Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2092939357","https://openalex.org/W2406067508","https://openalex.org/W2559767995","https://openalex.org/W2739529772","https://openalex.org/W2754517384","https://openalex.org/W2962894046","https://openalex.org/W2990123902","https://openalex.org/W3128395826","https://openalex.org/W4214717370","https://openalex.org/W4401109681","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6756256016","https://openalex.org/W6765407481","https://openalex.org/W6769196924","https://openalex.org/W6771807793","https://openalex.org/W6791110673","https://openalex.org/W6853445487"],"related_works":["https://openalex.org/W2163875935","https://openalex.org/W2053566994","https://openalex.org/W1550757207","https://openalex.org/W202303397","https://openalex.org/W2279821256","https://openalex.org/W2970690932","https://openalex.org/W2003770568","https://openalex.org/W2110715801","https://openalex.org/W2186435021","https://openalex.org/W588585258"],"abstract_inverted_index":{"Compared":[0],"with":[1,39,166],"traditional":[2],"pipelined":[3],"frameworks,":[4],"end-to-end":[5,30],"autonomous":[6],"driving":[7,59,82],"integrates":[8],"the":[9,57,63,88,97,108,113,118,122,126,131,139,145,151,158,167,174,179,187,199,218,222],"problems":[10],"of":[11,91,134,217],"perception,":[12],"decision-making,":[13],"planning,":[14],"and":[15,25,48,50,101,120,164,181,191,196,202,213],"control,":[16],"which":[17,161],"can":[18],"be":[19],"more":[20,26],"adaptive":[21],"to":[22,55,71,111,116,129,142,172,177,221],"complex":[23,36],"scenarios":[24],"generalizable.":[27],"However,":[28],"in":[29,35,66,198,210],"automated":[31],"driving,":[32],"especially":[33],"when":[34],"urban":[37],"roads":[38],"high-dimensional":[40],"observation":[41],"data,":[42],"reinforcement":[43,78],"learning":[44,79],"training":[45,183,195],"is":[46,53,155,162],"difficult":[47,54],"inefficient,":[49],"intelligence":[51],"exploration":[52,215],"find":[56],"best":[58],"strategy.":[60],"To":[61],"address":[62],"above":[64],"problems,":[65],"this":[67,149],"paper,":[68,150],"we":[69],"propose":[70],"use":[72,186],"maximized":[73],"value":[74,90],"conditional":[75,89,98],"state":[76,99,109,127,135,153],"entropy(VCSE)":[77],"for":[80,194],"automatic":[81],"strategy":[83],"learning.":[84],"The":[85],"method":[86,204],"estimates":[87],"each":[92],"state,":[93],"also":[94],"known":[95],"as":[96,157,171],"entropy,":[100],"then":[102],"maximizes":[103],"their":[104],"average":[105],"value,":[106],"increasing":[107],"entropy":[110,128,136,154],"encourage":[112,173],"intelligent":[114,140,175],"body":[115,141,176],"explore":[117,178],"environment,":[119],"at":[121],"same":[123,189],"time,":[124],"limiting":[125],"prevent":[130],"excessive":[132],"pursuit":[133],"from":[137],"causing":[138],"prefer":[143],"exploring":[144],"low-value":[146],"state.":[147],"In":[148],"value-conditional":[152],"used":[156],"intrinsic":[159],"reward,":[160,169],"weighted":[163],"summed":[165],"task":[168],"so":[170],"environment":[180,190,219],"improve":[182],"efficiency.":[184],"We":[185],"exact":[188],"traffic":[192],"flow":[193],"evaluation":[197],"Carla":[200],"simulator,":[201],"our":[203],"shows":[205],"a":[206],"large":[207],"performance":[208],"improvement":[209],"all":[211],"aspects":[212],"better":[214],"utilization":[216],"compared":[220],"baseline":[223],"method.":[224]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}