{"id":"https://openalex.org/W4402474348","doi":"https://doi.org/10.1109/ccece59415.2024.10667224","title":"LLM4RL: Enhancing Reinforcement Learning with Large Language Models","display_name":"LLM4RL: Enhancing Reinforcement Learning with Large Language Models","publication_year":2024,"publication_date":"2024-08-06","ids":{"openalex":"https://openalex.org/W4402474348","doi":"https://doi.org/10.1109/ccece59415.2024.10667224"},"language":"en","primary_location":{"id":"doi:10.1109/ccece59415.2024.10667224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccece59415.2024.10667224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","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/A5072694505","display_name":"Jiehan Zhou","orcid":"https://orcid.org/0000-0002-4026-1649"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiehan Zhou","raw_affiliation_strings":["Shandong University of Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024764459","display_name":"Yang Zhao","orcid":"https://orcid.org/0009-0001-3680-0240"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["Shandong University of Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114608863","display_name":"Jiahong Liu","orcid":"https://orcid.org/0009-0006-7076-0680"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahong Liu","raw_affiliation_strings":["Shandong University of Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111324339","display_name":"Peijun Dong","orcid":"https://orcid.org/0009-0006-9678-8411"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peijun Dong","raw_affiliation_strings":["Shandong University of Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081780695","display_name":"Xiaoyu Luo","orcid":"https://orcid.org/0000-0002-8753-4210"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Xiaoyu Luo","raw_affiliation_strings":["Kyung Hee University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyung Hee University,Seoul,South Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074353258","display_name":"Hang Tao","orcid":"https://orcid.org/0000-0002-6937-2289"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Tao","raw_affiliation_strings":["Shandong University of Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089159973","display_name":"Shi\u2010Chung Chang","orcid":"https://orcid.org/0000-0001-7595-2485"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shi Chang","raw_affiliation_strings":["University of Western Ontario,Department of Computer Science,London,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Ontario,Department of Computer Science,London,Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044870211","display_name":"Hanjiang Luo","orcid":"https://orcid.org/0000-0001-6796-9658"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanjiang Luo","raw_affiliation_strings":["Shandong University of Science and Technology,Qingdao,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,Qingdao,China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.778,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87212924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9381999969482422,"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":0.9381999969482422,"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":0.7813940048217773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744369387626648},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41913801431655884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4058656096458435},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3249337077140808},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13387644290924072}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7813940048217773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744369387626648},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41913801431655884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4058656096458435},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3249337077140808},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13387644290924072},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccece59415.2024.10667224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccece59415.2024.10667224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W4321011670","https://openalex.org/W4321472233","https://openalex.org/W4322825501","https://openalex.org/W4327525108","https://openalex.org/W4385970117","https://openalex.org/W4389821446","https://openalex.org/W4390603637","https://openalex.org/W4393763811","https://openalex.org/W4402716424","https://openalex.org/W6849548236","https://openalex.org/W6849861922","https://openalex.org/W6850101715","https://openalex.org/W6850833530","https://openalex.org/W6856012975"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Integrating":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"into":[5],"reinforcement":[6],"learning":[7,13,35,59],"(RL)":[8],"promises":[9],"to":[10],"enhance":[11],"the":[12],"performance.":[14],"Traditional":[15],"RL":[16],"faces":[17],"challenges":[18],"in":[19,43,61],"industrial":[20],"settings,":[21],"including":[22],"complex":[23],"environments,":[24],"safety":[25],"concerns,":[26],"and":[27,36,53],"multimodal":[28],"data.":[29],"As":[30],"powerful":[31],"tools":[32],"for":[33],"contextual":[34],"reasoning,":[37],"LLMs":[38],"can":[39,57],"address":[40],"issues":[41],"inherent":[42],"traditional":[44],"RL.":[45],"This":[46],"paper":[47],"introduces":[48],"a":[49],"generic":[50],"LLM4RL":[51,56],"framework,":[52],"investigates":[54],"how":[55],"improve":[58],"performance":[60],"autonomous":[62],"driving.":[63]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
