{"id":"https://openalex.org/W4400645782","doi":"https://doi.org/10.1109/iv55156.2024.10588690","title":"Inverse Reinforcement Learning with Failed Demonstrations towards Stable Driving Behavior Modeling","display_name":"Inverse Reinforcement Learning with Failed Demonstrations towards Stable Driving Behavior Modeling","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4400645782","doi":"https://doi.org/10.1109/iv55156.2024.10588690"},"language":"en","primary_location":{"id":"doi:10.1109/iv55156.2024.10588690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","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/A5091102986","display_name":"Minglu Zhao","orcid":"https://orcid.org/0000-0002-0338-0833"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Minglu Zhao","raw_affiliation_strings":["Tokyo Insititute of Technology,Department of Computer Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Insititute of Technology,Department of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032839697","display_name":"Masamichi Shimosaka","orcid":"https://orcid.org/0000-0003-0558-2006"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masamichi Shimosaka","raw_affiliation_strings":["Tokyo Insititute of Technology,Department of Computer Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Insititute of Technology,Department of Computer Science,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.5195,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62880738,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2537","last_page":"2544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9753000140190125,"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":0.9753000140190125,"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":0.9373000264167786,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9302999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7053782939910889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5782739520072937},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5623562932014465},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5173520445823669},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.49331918358802795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3902352750301361},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19469967484474182},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15981516242027283},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14536187052726746},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08728772401809692}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7053782939910889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5782739520072937},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5623562932014465},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5173520445823669},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.49331918358802795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3902352750301361},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19469967484474182},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15981516242027283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14536187052726746},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08728772401809692},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv55156.2024.10588690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1533707276","https://openalex.org/W1591675293","https://openalex.org/W1977828796","https://openalex.org/W2115923799","https://openalex.org/W2566837261","https://openalex.org/W2799151646","https://openalex.org/W3003474222","https://openalex.org/W3091362478","https://openalex.org/W3133456577","https://openalex.org/W4210909794","https://openalex.org/W4285812978","https://openalex.org/W4285819294","https://openalex.org/W4323796747","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6696273291","https://openalex.org/W6745935785","https://openalex.org/W6750186571","https://openalex.org/W6793060456"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Driving":[0],"behavior":[1],"modeling":[2],"is":[3],"crucial":[4],"in":[5,58,86,90],"autonomous":[6,18],"driving":[7,93],"systems":[8],"for":[9,76,113],"preventing":[10],"traffic":[11],"accidents.":[12],"Inverse":[13],"reinforcement":[14],"learning":[15],"(IRL)":[16],"allows":[17],"agents":[19],"to":[20,28,81],"learn":[21,31],"complicated":[22],"behaviors":[23,85],"from":[24],"expert":[25,45,121],"demonstrations.":[26,87,124],"Similar":[27],"how":[29],"humans":[30],"by":[32],"trial":[33],"and":[34,46,103,122],"error,":[35],"failed":[36,47,123],"demonstrations":[37,48],"can":[38],"help":[39,82],"an":[40,59],"agent":[41],"avoid":[42],"failures.":[43],"However,":[44],"generally":[49],"have":[50],"some":[51],"common":[52],"behaviors,":[53],"which":[54],"could":[55],"cause":[56],"instability":[57],"IRL":[60,80],"model.":[61],"To":[62],"improve":[63],"the":[64,77,84,97,118],"stability,":[65],"this":[66],"work":[67],"proposes":[68],"a":[69,91],"novel":[70],"method":[71,99],"that":[72,96],"introduces":[73],"time-series":[74],"labeling":[75],"optimization":[78],"of":[79,117,120],"distinguish":[83],"Experimental":[88],"results":[89,109],"simulated":[92],"environment":[94],"show":[95,111],"proposed":[98],"converged":[100],"faster":[101],"than":[102],"outperformed":[104],"other":[105],"baseline":[106],"methods.":[107],"The":[108],"also":[110],"consistency":[112],"various":[114],"data":[115],"balances":[116],"number":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}