{"id":"https://openalex.org/W4400528355","doi":"https://doi.org/10.1145/3626772.3657767","title":"Reinforcement Learning-based Recommender Systems with Large Language Models for State Reward and Action Modeling","display_name":"Reinforcement Learning-based Recommender Systems with Large Language Models for State Reward and Action Modeling","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400528355","doi":"https://doi.org/10.1145/3626772.3657767"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657767","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657767","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657767","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100440215","display_name":"Jie Wang","orcid":"https://orcid.org/0009-0005-7117-8580"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-7117-8580","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082408006","display_name":"Alexandros Karatzoglou","orcid":"https://orcid.org/0000-0001-6063-9023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandros Karatzoglou","raw_affiliation_strings":["Amazon, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6063-9023","affiliations":[{"raw_affiliation_string":"Amazon, Barcelona, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015760420","display_name":"Ioannis Arapakis","orcid":"https://orcid.org/0000-0003-2528-6597"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ioannis Arapakis","raw_affiliation_strings":["Telefonica Research, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2528-6597","affiliations":[{"raw_affiliation_string":"Telefonica Research, Barcelona, Spain","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9228-1759","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"375","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9869999885559082,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9864000082015991,"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":0.8500077724456787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032598495483398},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7054861187934875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6149108409881592},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5762720704078674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5110955834388733},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47571617364883423},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09708064794540405}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8500077724456787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032598495483398},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7054861187934875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6149108409881592},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5762720704078674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5110955834388733},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47571617364883423},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09708064794540405},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657767","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657767","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:323432","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657767","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657767","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1968563228","https://openalex.org/W2069870183","https://openalex.org/W2419128894","https://openalex.org/W2596585349","https://openalex.org/W2783272285","https://openalex.org/W2788295351","https://openalex.org/W2902040508","https://openalex.org/W2963367478","https://openalex.org/W2964108915","https://openalex.org/W2971196067","https://openalex.org/W3034791416","https://openalex.org/W3034853385","https://openalex.org/W3035170973","https://openalex.org/W3102778384","https://openalex.org/W3185341429","https://openalex.org/W3211540990","https://openalex.org/W4212961739","https://openalex.org/W4226278401","https://openalex.org/W4284702156","https://openalex.org/W4290944002","https://openalex.org/W4296591867","https://openalex.org/W4378465281","https://openalex.org/W4382246105","https://openalex.org/W4384652161","https://openalex.org/W4386081001","https://openalex.org/W4386729449","https://openalex.org/W4387848745","https://openalex.org/W4400118952","https://openalex.org/W6601897980"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4317039510","https://openalex.org/W4238861846","https://openalex.org/W790944756"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)-based":[2],"recommender":[3],"systems":[4],"have":[5],"demonstrated":[6],"promising":[7],"performance":[8,156],"in":[9,183],"session-based":[10],"and":[11,39,57,90,114,163,171,180,189],"sequential":[12,18],"recommendation":[13,19,45,155],"tasks.":[14],"Existing":[15],"offline":[16,96,142],"RL-based":[17,69],"methods":[20],"face":[21],"the":[22,30,36,84,111,130,140,160,164,168,178],"challenge":[23],"of":[24,78],"obtaining":[25],"effective":[26],"user":[27,37,93,112,125,173],"feedback":[28,94],"from":[29,75],"environment.":[31],"Developing":[32],"a":[33,47,76,102,118,147],"model":[34,104,120],"for":[35,44,86,95],"state":[38,103],"shaping":[40],"an":[41,64],"appropriate":[42],"reward":[43,119,181],"remains":[46],"challenge.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"leverage":[53],"language":[54,60],"understanding":[55],"capabilities":[56],"adapt":[58],"large":[59,87],"models":[61,182],"(LLMs)":[62],"as":[63,101,117],"environment":[65],"(LE)":[66],"to":[67,121,134,152],"enhance":[68],"recommenders.":[70],"The":[71],"LE":[72,131,148],"is":[73],"learned":[74],"subset":[77],"user-item":[79],"interaction":[80],"data,":[81,89],"thus":[82],"reducing":[83],"need":[85],"training":[88,143],"can":[91],"synthesize":[92],"data":[97],"by:":[98],"(i)":[99],"acting":[100],"that":[105,109,138],"produces":[106],"high-quality":[107],"states":[108],"enrich":[110],"representation,":[113],"(ii)":[115],"functioning":[116],"accurately":[122],"capture":[123],"nuanced":[124],"preferences":[126],"on":[127,193],"actions.":[128],"Moreover,":[129],"allows":[132],"us":[133],"generate":[135],"positive":[136],"actions":[137,170],"augment":[139],"limited":[141],"data.":[144],"We":[145,175],"propose":[146],"Augmentation":[149],"(LEA)":[150],"method":[151],"further":[153],"improve":[154],"by":[157],"optimising":[158],"jointly":[159],"supervised":[161],"component":[162],"RL":[165,187],"policy,":[166],"using":[167],"augmented":[169],"historical":[172],"signals.":[174],"use":[176],"LEA,":[177],"state,":[179],"conjunction":[184],"with":[185],"state-of-the-art":[186],"recommenders":[188],"report":[190],"experimental":[191],"results":[192],"two":[194],"publicly":[195],"available":[196],"datasets.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}