{"id":"https://openalex.org/W4413141447","doi":"https://doi.org/10.1109/tnnls.2025.3590731","title":"Improving Sample Efficiency of Reinforcement Learning With Background Knowledge From Large Language Models","display_name":"Improving Sample Efficiency of Reinforcement Learning With Background Knowledge From Large Language Models","publication_year":2025,"publication_date":"2025-08-14","ids":{"openalex":"https://openalex.org/W4413141447","doi":"https://doi.org/10.1109/tnnls.2025.3590731","pmid":"https://pubmed.ncbi.nlm.nih.gov/40811163"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3590731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3590731","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102924801","display_name":"Fuxiang Zhang","orcid":"https://orcid.org/0009-0001-7251-4372"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuxiang Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-7251-4372","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103160581","display_name":"Junyou Li","orcid":"https://orcid.org/0000-0002-8959-9122"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyou Li","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108326018","display_name":"Yi-Chen Li","orcid":"https://orcid.org/0009-0004-9908-5303"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Chen Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-9908-5303","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongzhang Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9238-4747","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101458462","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1052-5447"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1052-5447","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deheng Ye","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1754-1837","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94145206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"36","issue":"11","first_page":"19681","last_page":"19692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"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/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"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":0.9781000018119812,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.949999988079071,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7756215333938599},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7445114254951477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6792757511138916},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6417078971862793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5840072631835938},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.44843241572380066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4395596385002136},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4311600923538208},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22424235939979553},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11170497536659241},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.10993778705596924},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.10524016618728638},{"id":"https://openalex.org/keywords/developmental-psychology","display_name":"Developmental psychology","score":0.09273558855056763},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07812914252281189},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07727333903312683}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7756215333938599},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7445114254951477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6792757511138916},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6417078971862793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5840072631835938},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.44843241572380066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4395596385002136},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4311600923538208},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22424235939979553},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11170497536659241},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.10993778705596924},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.10524016618728638},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.09273558855056763},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07812914252281189},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07727333903312683},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3590731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3590731","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40811163","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40811163","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5091473533","display_name":null,"funder_award_id":"62250069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6406246630","display_name":null,"funder_award_id":"62276126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2763110165","https://openalex.org/W2877093712","https://openalex.org/W2896457183","https://openalex.org/W2963523627","https://openalex.org/W2964654516","https://openalex.org/W2964915587","https://openalex.org/W2970641574","https://openalex.org/W4220747123","https://openalex.org/W4385568182","https://openalex.org/W4385571232","https://openalex.org/W4385644834","https://openalex.org/W4385734161","https://openalex.org/W4390264450","https://openalex.org/W4393065402","https://openalex.org/W4393147610","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2388888344"],"abstract_inverted_index":{"Low":[0],"sample":[1,153],"efficiency":[2,154],"is":[3,38],"an":[4,63],"enduring":[5],"challenge":[6],"of":[7,14,62,69,99,159],"reinforcement":[8],"learning":[9,28],"(RL).":[10],"With":[11],"the":[12,70,100,105],"advent":[13],"versatile":[15],"large":[16],"language":[17],"models":[18],"(LLMs),":[19],"recent":[20],"works":[21],"impart":[22],"common-sense":[23],"knowledge":[24,61,81,98,107],"to":[25,58,95,131],"accelerate":[26],"policy":[27,122],"for":[29,41,111,120,134],"RL":[30,76],"processes.":[31],"However,":[32],"we":[33,51,103],"note":[34],"that":[35,55,148],"such":[36],"guidance":[37],"often":[39],"tailored":[40],"one":[42],"specific":[43],"task":[44,125],"but":[45],"loses":[46],"generalizability.":[47],"In":[48],"this":[49],"article,":[50],"introduce":[52],"a":[53,88,117,157],"framework":[54],"harnesses":[56],"LLMs":[57,85,133],"extract":[59],"background":[60,97,135],"environment,":[64,72],"which":[65,115],"contains":[66],"general":[67],"understandings":[68],"entire":[71],"making":[73],"various":[74],"downstream":[75,160],"tasks":[77,161],"benefit":[78],"from":[79,124,162],"one-time":[80],"representation.":[82],"We":[83,127],"ground":[84],"by":[86],"feeding":[87],"few":[89],"precollected":[90],"experiences":[91],"and":[92,142,164],"requesting":[93],"them":[94],"delineate":[96],"environment.":[101],"Afterward,":[102],"represent":[104],"output":[106],"as":[108],"potential":[109],"functions":[110],"potential-based":[112],"reward":[113],"shaping,":[114],"has":[116],"good":[118],"property":[119],"maintaining":[121],"optimality":[123],"rewards.":[126],"instantiate":[128],"three":[129],"variants":[130],"prompt":[132],"knowledge,":[136],"including":[137],"writing":[138],"code,":[139],"annotating":[140],"pReferences,":[141],"assigning":[143],"goals.":[144],"Our":[145],"experiments":[146],"show":[147],"these":[149],"methods":[150],"achieve":[151],"significant":[152],"improvements":[155],"in":[156],"spectrum":[158],"Minigrid":[163],"Crafter":[165],"domains.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}