{"id":"https://openalex.org/W4402352501","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650538","title":"Real-time Integration of Fine-tuned Large Language Model for Improved Decision-Making in Reinforcement Learning","display_name":"Real-time Integration of Fine-tuned Large Language Model for Improved Decision-Making in Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352501","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650538"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5111319843","display_name":"Xiancai Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiancai Xiang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113757935","display_name":"Jian Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Xue","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351935","display_name":"Lin Zhao","orcid":"https://orcid.org/0000-0003-2567-627X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Lei","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109778682","display_name":"Chao Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yue","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072833759","display_name":"Ke L\u00fc","orcid":"https://orcid.org/0000-0003-0176-3088"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.778,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87191593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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":0.9980999827384949,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.972100019454956,"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/T10260","display_name":"Software Engineering Research","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8361961841583252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7071389555931091},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6163942813873291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4707237780094147},{"id":"https://openalex.org/keywords/decision-making-models","display_name":"Decision-making models","score":0.41076183319091797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3295786380767822},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15232941508293152},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06920471787452698}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8361961841583252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071389555931091},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6163942813873291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4707237780094147},{"id":"https://openalex.org/C2888476","wikidata":"https://www.wikidata.org/wiki/Q5249202","display_name":"Decision-making models","level":2,"score":0.41076183319091797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3295786380767822},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15232941508293152},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06920471787452698}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2023857055","https://openalex.org/W2767056494","https://openalex.org/W2883057932","https://openalex.org/W2896457183","https://openalex.org/W2963761716","https://openalex.org/W3093887912","https://openalex.org/W3095669803","https://openalex.org/W3130800560","https://openalex.org/W3138984732","https://openalex.org/W3165228974","https://openalex.org/W4220747123","https://openalex.org/W4285294723","https://openalex.org/W4292779060","https://openalex.org/W4303443398","https://openalex.org/W4306786778","https://openalex.org/W4321011670","https://openalex.org/W4323651349","https://openalex.org/W4378505261","https://openalex.org/W4378508644","https://openalex.org/W4378510404","https://openalex.org/W4379924706","https://openalex.org/W4383108457","https://openalex.org/W4401042832","https://openalex.org/W4401414087","https://openalex.org/W4401416363","https://openalex.org/W6753207554","https://openalex.org/W6778883912","https://openalex.org/W6784678651","https://openalex.org/W6785204124","https://openalex.org/W6846002521"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"this":[1,114],"paper,":[2],"we":[3,186],"investigate":[4],"a":[5,100,106,145,151,188],"novel":[6,189],"and":[7,50,96,224,250],"efficacious":[8],"methodology":[9],"for":[10,40,93],"training":[11,37,238,269],"reinforcement":[12,221],"learning":[13,222],"agents.":[14,73],"We":[15,139,214],"also":[16],"further":[17],"reveal":[18,232],"the":[19,22,45,54,65,69,80,86,118,122,142,160,179,184,201,208,216,235,240,245,248,251,256,267],"potential":[20],"of":[21,47,58,71,82,88,91,121,162,172,181,205,210,247,258],"Large":[23,195],"Language":[24,196],"Model":[25,197],"(LLM)":[26],"in":[27,36,79,244,260],"intricate":[28],"decision-making":[29,38,132,203],"environments.":[30],"Reinforcement":[31],"learning,":[32],"one":[33],"main":[34],"approach":[35,190],"capabilities":[39],"intelligent":[41,72],"agents,":[42],"suffers":[43],"from":[44,111],"challenges":[46],"sparse":[48],"rewards":[49],"inefficient":[51],"exploration.":[52],"Considering":[53],"current":[55],"phenomenal":[56],"performance":[57,257],"pre-trained":[59],"LLMs,":[60,83],"certain":[61],"studies":[62],"have":[63],"adopted":[64],"LLMs":[66,92,97,143],"to":[67,144,199],"shepherd":[68],"actions":[70],"However,":[74],"there":[75],"are":[76],"some":[77],"limitations":[78],"application":[81],"such":[84],"as":[85],"lack":[87],"domain":[89],"knowledge":[90,152,252],"specific":[94],"fields,":[95],"generally":[98],"access":[99],"slower":[101],"response":[102],"time":[103],"but":[104],"consume":[105],"higher":[107],"economic":[108],"cost.":[109],"Embarking":[110],"these":[112],"constraints,":[113],"paper":[115],"takes":[116],"on":[117],"formidable":[119],"challenge":[120],"Unmanned":[123],"Air":[124],"Vehicle":[125],"(UAV)":[126],"air":[127,163,211,261],"combat":[128,212,262],"simulations":[129],"environment,":[130],"where":[131],"is":[133],"notably":[134],"circumscribed":[135],"by":[136,219,227],"temporal":[137],"limitations.":[138],"initially":[140],"fine-tuned":[141],"domain-specific":[146],"expertise":[147],"while":[148,264],"concurrently":[149,265],"constructing":[150],"base.":[153],"Hence,":[154],"upon":[155],"gaining":[156],"profound":[157],"insight":[158],"into":[159,167],"field":[161],"combat,":[164],"it":[165],"evolves":[166],"an":[168],"adept":[169],"model":[170],"capable":[171],"effectively":[173],"guiding":[174],"UAV":[175],"decisions.":[176],"Further":[177],"addressing":[178],"difficulties":[180],"real-time":[182],"accessing":[183],"LLM,":[185],"propose":[187],"named":[191],"Reward":[192],"Shaping":[193],"with":[194],"(LLM-RS)":[198],"augment":[200],"autonomous":[202],"competency":[204],"UAVs":[206,259],"within":[207],"context":[209],"simulations.":[213],"compared":[215],"agents":[217],"trained":[218,226],"conventional":[220],"techniques":[223],"those":[225],"LLM-RS.":[228],"The":[229],"experimental":[230],"results":[231],"that,":[233],"under":[234],"same":[236],"equipment":[237],"conditions,":[239],"LLM-RS":[241],"technique":[242],"grounded":[243],"fine-tuning":[246],"LLM":[249],"base":[253],"substantially":[254],"improves":[255],"simulations,":[263],"diminishing":[266],"requisite":[268],"duration.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}