{"id":"https://openalex.org/W4408399515","doi":"https://doi.org/10.1109/lra.2025.3551098","title":"<b>L</b>anguage-<b>D</b>riven <b>P</b>olicy <b>D</b>istillation for Cooperative Driving in Multi-Agent Reinforcement Learning","display_name":"<b>L</b>anguage-<b>D</b>riven <b>P</b>olicy <b>D</b>istillation for Cooperative Driving in Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408399515","doi":"https://doi.org/10.1109/lra.2025.3551098"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3551098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3551098","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5028854703","display_name":"Jiaqi Liu","orcid":"https://orcid.org/0000-0002-6171-6155"},"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":"Jiaqi Liu","raw_affiliation_strings":["College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6171-6155","affiliations":[{"raw_affiliation_string":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111339820","display_name":"Chengkai Xu","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":"Chengkai Xu","raw_affiliation_strings":["College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-6714-3004","affiliations":[{"raw_affiliation_string":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055911707","display_name":"Peng Hang","orcid":"https://orcid.org/0000-0002-5843-0594"},"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":"Peng Hang","raw_affiliation_strings":["College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5843-0594","affiliations":[{"raw_affiliation_string":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062319704","display_name":"Jian Sun","orcid":"https://orcid.org/0000-0001-5031-4938"},"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":"Jian Sun","raw_affiliation_strings":["College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5031-4938","affiliations":[{"raw_affiliation_string":"College of Transportation and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022382771","display_name":"Mingyu Ding","orcid":"https://orcid.org/0000-0001-6556-8359"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyu Ding","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","Department of Computer Science, University of North Carolina, Chapel Hill, NC, USA"],"raw_orcid":"https://orcid.org/0000-0001-6556-8359","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"Department of Computer Science, University of North Carolina, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770873","display_name":"Wei Zhan","orcid":"https://orcid.org/0000-0002-1474-1200"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhan","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA","Department of Mechanical Engineering, the University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1474-1200","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Mechanical Engineering, the University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA","Department of Mechanical Engineering, the University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0206-6639","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Mechanical Engineering, the University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.772,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97663847,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"10","issue":"5","first_page":"4292","last_page":"4299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6069999933242798,"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":0.6069999933242798,"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/group-b","display_name":"Group B","score":0.41900312900543213},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.14366337656974792},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.054419517517089844}],"concepts":[{"id":"https://openalex.org/C2777785397","wikidata":"https://www.wikidata.org/wiki/Q492194","display_name":"Group B","level":2,"score":0.41900312900543213},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.14366337656974792},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.054419517517089844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3551098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3551098","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W1965455100","https://openalex.org/W2056877664","https://openalex.org/W3147987103","https://openalex.org/W4221145253","https://openalex.org/W4311887664","https://openalex.org/W4313586500","https://openalex.org/W4360584590","https://openalex.org/W4367309555","https://openalex.org/W4381733136","https://openalex.org/W4383109478","https://openalex.org/W4391216549","https://openalex.org/W4399990060","https://openalex.org/W4401023826","https://openalex.org/W4401894891","https://openalex.org/W4404985202","https://openalex.org/W4408655515","https://openalex.org/W4408696314","https://openalex.org/W6604518663","https://openalex.org/W6743802245","https://openalex.org/W6840380725","https://openalex.org/W6846254642","https://openalex.org/W6853347896","https://openalex.org/W6857112689","https://openalex.org/W6864695429","https://openalex.org/W6867658008","https://openalex.org/W6868270293","https://openalex.org/W6872648459","https://openalex.org/W6872810703"],"related_works":["https://openalex.org/W1536372821","https://openalex.org/W2558446188","https://openalex.org/W4200103860","https://openalex.org/W2121556643","https://openalex.org/W2579083402","https://openalex.org/W2066096579","https://openalex.org/W1890492875","https://openalex.org/W2318761088","https://openalex.org/W2070137188","https://openalex.org/W2400914179"],"abstract_inverted_index":{"The":[0,118,151,168],"cooperative":[1,34,76,111,133],"driving":[2],"technology":[3],"of":[4,18,46,75,125],"Connected":[5],"and":[6,16,49,61,82,127,185,200],"Autonomous":[7],"Vehicles":[8],"(CAVs)":[9],"is":[10],"crucial":[11],"for":[12,92],"improving":[13],"the":[14,72,122,156,172,183,188],"efficiency":[15,48,81,202],"safety":[17],"transportation":[19],"systems.":[20],"Learning-based":[21],"methods,":[22],"such":[23],"as":[24],"Multi-Agent":[25],"Reinforcement":[26],"Learning":[27],"(MARL),":[28],"have":[29,58],"demonstrated":[30],"strong":[31],"capabilities":[32,74,178],"in":[33,44,65],"decision-making":[35,68,80,112,116,134,141],"tasks.":[36,69],"However,":[37],"existing":[38],"MARL":[39,94],"approaches":[40],"still":[41],"face":[42],"challenges":[43],"terms":[45],"learning":[47,73,201],"performance.":[50,190],"In":[51,96],"recent":[52],"years,":[53],"Large":[54],"Language":[55],"Models":[56],"(LLMs)":[57],"rapidly":[59,175],"advanced":[60],"shown":[62],"remarkable":[63],"abilities":[64],"various":[66],"sequential":[67],"To":[70],"enhance":[71],"agents":[77,108],"while":[78],"ensuring":[79],"cost-effectiveness,":[83],"we":[84],"propose":[85],"LDPD,":[86],"a":[87,99],"language-driven":[88],"policy":[89,166],"distillation":[90],"method":[91],"guiding":[93],"exploration.":[95],"this":[97],"framework,":[98],"teacher":[100,119,184],"agent":[101,120,153],"based":[102],"on":[103],"LLM":[104],"trains":[105],"smaller":[106],"student":[107,152],"to":[109,130,143,204],"achieve":[110,144],"through":[113,164],"its":[114,161],"own":[115,162],"demonstrations.":[117],"enhances":[121],"observation":[123],"information":[124],"CAVs":[126],"utilizes":[128],"LLMs":[129],"perform":[131],"complex":[132],"reasoning,":[135],"which":[136],"also":[137],"leverages":[138],"carefully":[139],"designed":[140],"tools":[142],"expert-level":[145],"decisions,":[146],"providing":[147],"high-quality":[148],"teaching":[149],"experiences.":[150],"then":[154],"refines":[155],"teacher's":[157,189],"prior":[158],"knowledge":[159],"into":[160],"model":[163],"gradient":[165],"updates.":[167],"experiments":[169,192],"demonstrate":[170],"that":[171,194],"students":[173],"can":[174],"improve":[176],"their":[177],"with":[179],"minimal":[180],"guidance":[181],"from":[182],"eventually":[186],"surpass":[187],"Extensive":[191],"show":[193],"our":[195],"approach":[196],"demonstrates":[197],"better":[198],"performance":[199],"compared":[203],"baseline":[205],"methods.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}