{"id":"https://openalex.org/W4412377950","doi":"https://doi.org/10.1145/3726302.3730322","title":"Reassessing the Effectiveness of Reinforcement Learning based Recommender Systems for Sequential Recommendation","display_name":"Reassessing the Effectiveness of Reinforcement Learning based Recommender Systems for Sequential Recommendation","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377950","doi":"https://doi.org/10.1145/3726302.3730322"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730322","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730322","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055479137","display_name":"Dilina Chandika Rajapakse","orcid":"https://orcid.org/0000-0001-9722-9108"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Dilina Chandika Rajapakse","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005545405","display_name":"Dietmar Jannach","orcid":"https://orcid.org/0000-0002-4698-8507"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dietmar Jannach","raw_affiliation_strings":["University of Klagenfurt, Klagenfurt, Austria"],"affiliations":[{"raw_affiliation_string":"University of Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055479137"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28546425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3306","last_page":"3314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9868999719619751,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8756203651428223},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8668577671051025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701629400253296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319068491458893},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4145803451538086}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8756203651428223},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8668577671051025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701629400253296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319068491458893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4145803451538086}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730322","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730322","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730322","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730322","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377950.pdf","grobid_xml":"https://content.openalex.org/works/W4412377950.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2006996936","https://openalex.org/W2069065514","https://openalex.org/W2562236173","https://openalex.org/W2626454364","https://openalex.org/W2783272285","https://openalex.org/W2809307135","https://openalex.org/W2902040508","https://openalex.org/W2910577570","https://openalex.org/W2957191877","https://openalex.org/W2963367478","https://openalex.org/W2964044287","https://openalex.org/W2972941122","https://openalex.org/W2982267219","https://openalex.org/W2984100107","https://openalex.org/W2987577970","https://openalex.org/W3034853385","https://openalex.org/W3088777230","https://openalex.org/W3093891819","https://openalex.org/W3102619277","https://openalex.org/W3123348991","https://openalex.org/W3125645198","https://openalex.org/W3134624922","https://openalex.org/W3199047808","https://openalex.org/W3206324923","https://openalex.org/W3211255867","https://openalex.org/W3211540990","https://openalex.org/W4212961739","https://openalex.org/W4229000037","https://openalex.org/W4297794619","https://openalex.org/W4318159260","https://openalex.org/W4318710454","https://openalex.org/W4376873982","https://openalex.org/W4384652161","https://openalex.org/W4386729058","https://openalex.org/W4386729258","https://openalex.org/W4387031395","https://openalex.org/W4400261185","https://openalex.org/W4403220390"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Over":[0],"the":[1,8,46,69,85,94,105,112,121,125,139,143,161,165,191],"past":[2,96],"few":[3],"years,":[4],"researchers":[5],"have":[6],"explored":[7],"use":[9,166],"of":[10,59,107,157,167,170,193],"reinforcement":[11],"learning":[12,64,79,133],"(RL)":[13],"for":[14,195],"sequential":[15,109,196],"recommendation":[16,197],"problems.":[17],"However,":[18],"since":[19],"RL":[20,61,86,194],"techniques":[21],"commonly":[22],"target":[23],"at":[24],"optimizing":[25],"long-term":[26],"rewards,":[27],"it":[28],"is":[29,151],"surprising":[30],"that":[31,55,84,92,130,149,164],"RL-based":[32],"models":[33,42,134,172],"are":[34],"reported":[35,56,123],"to":[36,89,103,119,175,188],"be":[37],"competitive":[38],"with":[39,62],"traditional":[40],"supervised":[41,63,132],"when":[43],"evaluated":[44],"under":[45],"myopic":[47],"next-item":[48],"prediction":[49],"protocol.":[50],"A":[51],"recent":[52],"study":[53],"suggests":[54],"performance":[57,106],"gains":[58],"combining":[60],"techniques,":[65],"as":[66],"done":[67],"in":[68,111,124,155,160],"Self-Supervised":[70],"Q-Learning":[71],"(SQN)":[72],"framework,":[73],"may":[74,173],"actually":[75],"not":[76],"come":[77],"from":[78,142],"an":[80],"optimal":[81],"policy,":[82],"but":[83],"component":[87],"helps":[88],"learn":[90],"embeddings":[91],"encode":[93],"users'":[95],"interactions.":[97],"Given":[98],"these":[99],"observations,":[100],"we":[101,116,128],"aimed":[102],"reassess":[104],"RL-enhanced":[108],"recommendations":[110],"SQN":[113],"framework.":[114],"While":[115],"were":[117],"able":[118],"reproduce":[120],"results":[122],"respective":[126],"papers,":[127],"found":[129],"properly-tuned":[131],"like":[135],"GRU4Rec":[136],"substantially":[137],"outperform":[138],"proposed":[140],"RL-models":[141],"literature.":[144],"Our":[145],"analyses":[146],"furthermore":[147],"revealed":[148],"there":[150],"a":[152],"significant":[153],"inconsistency":[154],"terms":[156],"evaluation":[158,184],"protocols":[159],"literature,":[162],"and":[163,182],"third-party":[168],"implementations":[169],"existing":[171],"lead":[174],"unreliable":[176],"conclusions.":[177],"Overall,":[178],"still":[179],"more":[180],"research":[181],"alternative":[183],"schemes":[185],"seem":[186],"required":[187],"fully":[189],"leverage":[190],"power":[192],"tasks.":[198]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}