{"id":"https://openalex.org/W4402351402","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650400","title":"Rethinking Offline Reinforcement Learning for Sequential Recommendation from A Pair-Wise Q-Learning Perspective","display_name":"Rethinking Offline Reinforcement Learning for Sequential Recommendation from A Pair-Wise Q-Learning Perspective","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351402","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650400"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650400","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650400","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":"article","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/A5002602724","display_name":"Runqi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runqi Yang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004545610","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2399-2829"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Yu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382306","display_name":"Zhi Li","orcid":"https://orcid.org/0000-0002-8061-7486"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760682","display_name":"Shaohui Li","orcid":"https://orcid.org/0000-0002-9650-8874"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052639977","display_name":"Likang Wu","orcid":"https://orcid.org/0000-0002-4929-8587"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Likang Wu","raw_affiliation_strings":["University of Science and Technology of China,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9890000224113464,"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":0.8964234590530396},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7740081548690796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.703821063041687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5040275454521179},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5029441714286804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4617026448249817}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8964234590530396},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7740081548690796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703821063041687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5040275454521179},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5029441714286804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4617026448249817}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650400","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650400","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1568922908","https://openalex.org/W1924770834","https://openalex.org/W2054141820","https://openalex.org/W2120339295","https://openalex.org/W2138108551","https://openalex.org/W2140310134","https://openalex.org/W2145339207","https://openalex.org/W2149008295","https://openalex.org/W2171279286","https://openalex.org/W2171928131","https://openalex.org/W2209913494","https://openalex.org/W2618530766","https://openalex.org/W2626454364","https://openalex.org/W2783272285","https://openalex.org/W2788295351","https://openalex.org/W2809112621","https://openalex.org/W2809162153","https://openalex.org/W2896457183","https://openalex.org/W2897405591","https://openalex.org/W2899771611","https://openalex.org/W2902040508","https://openalex.org/W2902572901","https://openalex.org/W2963367478","https://openalex.org/W2963842088","https://openalex.org/W2964296635","https://openalex.org/W2984100107","https://openalex.org/W2984869362","https://openalex.org/W3033324992","https://openalex.org/W3034853385","https://openalex.org/W3034891407","https://openalex.org/W3035170973","https://openalex.org/W3102619277","https://openalex.org/W3102778384","https://openalex.org/W3123348991","https://openalex.org/W3147409906","https://openalex.org/W3156844209","https://openalex.org/W3173984942","https://openalex.org/W3194671304","https://openalex.org/W3205794883","https://openalex.org/W3206324923","https://openalex.org/W3211540990","https://openalex.org/W4230563027","https://openalex.org/W4284702156","https://openalex.org/W4298857966","https://openalex.org/W4299286960","https://openalex.org/W4366572482","https://openalex.org/W4385245566","https://openalex.org/W6630221451","https://openalex.org/W6632885370","https://openalex.org/W6636888537","https://openalex.org/W6637967152","https://openalex.org/W6640212811","https://openalex.org/W6680830989","https://openalex.org/W6692935382","https://openalex.org/W6755207826","https://openalex.org/W6756040250","https://openalex.org/W6757469721","https://openalex.org/W6759896672","https://openalex.org/W6769700555","https://openalex.org/W6779265984","https://openalex.org/W6802659552","https://openalex.org/W6922480057"],"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":{"Sequential":[0],"recommendations":[1],"have":[2,20],"gained":[3],"great":[4,44],"attention":[5],"in":[6,54],"recent":[7],"years.":[8],"Considering":[9],"that":[10],"user":[11,69,110],"interactions":[12],"naturally":[13],"follow":[14],"sequential":[15,29],"decision":[16],"tasks,":[17],"many":[18],"researchers":[19],"explored":[21],"the":[22,32,166],"integration":[23],"of":[24,109,169],"Reinforcement":[25],"Learning":[26],"(RL)":[27],"into":[28],"recommendations.":[30],"However,":[31],"limited":[33],"exploration":[34],"gap":[35],"between":[36],"recommender":[37],"systems":[38],"and":[39,78,123,134,151,163],"other":[40],"RL":[41,66,91],"scenarios":[42],"brings":[43],"challenges.":[45],"Fortunately,":[46],"Offline":[47],"RL,":[48],"which":[49],"learns":[50],"from":[51],"expert":[52],"experiences":[53],"offline":[55,65,90],"datasets,":[56,160],"has":[57],"emerged":[58],"as":[59],"a":[60,88,100,106,113,126,135],"potential":[61],"solution.":[62],"Nevertheless,":[63],"utilizing":[64],"to":[67,74,104,120,139],"model":[68,76,147],"preferences":[70],"is":[71],"non-trivial":[72],"due":[73],"strict":[75],"overestimation":[77,122],"implicit":[79,141],"feedback":[80],"issues.":[81],"To":[82],"address":[83],"these":[84],"challenges,":[85],"we":[86],"propose":[87],"novel":[89],"framework":[92],"called":[93],"Pair-Wise":[94],"Q-Learning":[95,115,150],"(PQL).":[96],"Our":[97],"approach":[98,116],"includes":[99],"state":[101],"encoder":[102],"module":[103,138],"generate":[105],"unified":[107],"representation":[108],"interaction":[111],"states,":[112],"conservative":[114,149],"with":[117],"double":[118],"Q-Networks":[119],"reduce":[121],"enhance":[124],"robustness,":[125],"dynamic":[127],"negative":[128],"sampling":[129],"strategy":[130],"based":[131],"on":[132,156],"Q-values,":[133],"pair-wise":[136,152],"learning":[137],"handle":[140],"feedback.":[142],"We":[143],"jointly":[144],"optimize":[145],"our":[146,170],"using":[148],"learning.":[153],"Experimental":[154],"results":[155],"two":[157],"real-world":[158],"e-commerce":[159],"considering":[161],"clicks":[162],"purchases,":[164],"demonstrate":[165],"superior":[167],"performance":[168],"proposed":[171],"PQL":[172],"over":[173],"existing":[174],"methods.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}