{"id":"https://openalex.org/W4411550039","doi":"https://doi.org/10.1145/3701716.3715547","title":"Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems","display_name":"Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4411550039","doi":"https://doi.org/10.1145/3701716.3715547"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.22112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078818673","display_name":"Wenzheng Shu","orcid":"https://orcid.org/0009-0004-7469-1083"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenzheng Shu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0004-7469-1083","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108783729","display_name":"Y. J. Zeng","orcid":"https://orcid.org/0000-0003-3749-4019"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiang Zeng","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3749-4019","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102214282","display_name":"Yongxiang Tang","orcid":"https://orcid.org/0000-0003-1614-2444"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxiang Tang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1614-2444","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033314210","display_name":"Teng Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Sha","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9386-8859","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ning Luo","orcid":"https://orcid.org/0009-0009-4984-5307"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Luo","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4984-5307","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004503830","display_name":"Yanhua Cheng","orcid":"https://orcid.org/0009-0005-8926-8605"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Cheng","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8926-8605","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053988193","display_name":"Xialong Liu","orcid":"https://orcid.org/0000-0001-7253-0674"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xialong Liu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7253-0674","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403505","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-8038-8150"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-8038-8150","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001339397","display_name":"Peng Jiang","orcid":"https://orcid.org/0000-0002-9266-0780"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jiang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9266-0780","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5078818673"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16234011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1308","last_page":"1311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.993399977684021,"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/recommender-system","display_name":"Recommender system","score":0.8930166363716125},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8260893821716309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7873834371566772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4434594213962555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4253884255886078}],"concepts":[{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8930166363716125},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8260893821716309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873834371566772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4434594213962555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4253884255886078}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3701716.3715547","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.22112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22112","pdf_url":"https://arxiv.org/pdf/2506.22112","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.22112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22112","pdf_url":"https://arxiv.org/pdf/2506.22112","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2009551863","https://openalex.org/W2020631728","https://openalex.org/W2604662567","https://openalex.org/W2950624398","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034853385","https://openalex.org/W3037440645","https://openalex.org/W4288319859","https://openalex.org/W4292419518","https://openalex.org/W4383993482","https://openalex.org/W4384644330","https://openalex.org/W4400528915","https://openalex.org/W4403577822","https://openalex.org/W6777656069"],"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":{"Offline":[0],"reinforcement":[1],"learning":[2,17],"(RL)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,55,113],"prevalent":[8],"and":[9,22,68,133,148],"effective":[10],"methodology":[11],"for":[12,41,88,108],"real-world":[13],"recommender":[14],"systems,":[15],"enabling":[16],"policies":[18],"from":[19],"historical":[20],"data":[21],"capturing":[23],"user":[24],"preferences.":[25],"In":[26],"offline":[27,82],"RL,":[28],"reward":[29,103],"shaping":[30],"encounters":[31],"significant":[32],"challenges,":[33],"with":[34,112,120],"past":[35],"efforts":[36],"to":[37,43,97,110,126],"incorporate":[38],"prior":[39],"strategies":[40],"uncertainty":[42,96],"improve":[44],"world":[45,66,146],"models":[46,67,147],"or":[47],"penalize":[48],"underexplored":[49],"state-action":[50],"pairs.":[51],"Despite":[52],"these":[53],"efforts,":[54],"critical":[56],"gap":[57],"remains:":[58],"the":[59,69,99,143,151,155],"simultaneous":[60],"balancing":[61],"of":[62,71,145,154],"intrinsic":[63,100],"biases":[64],"in":[65,102],"diversity":[70,107],"policy":[72],"recommendations.":[73],"To":[74],"address":[75],"this":[76],"limitation,":[77],"we":[78,105],"present":[79],"an":[80],"innovative":[81],"RL":[83],"framework":[84],"termed":[85],"Reallocated":[86],"Reward":[87],"Recommender":[89],"Systems":[90],"(R3S).":[91],"By":[92],"integrating":[93],"inherent":[94],"model":[95],"tackle":[98],"fluctuations":[101],"predictions,":[104],"boost":[106],"decision-making":[109],"align":[111],"more":[114],"interactive":[115],"paradigm,":[116],"incorporating":[117],"extra":[118],"penalizers":[119],"decay":[121],"that":[122,140],"deter":[123],"actions":[124],"leading":[125],"diminished":[127],"state":[128],"variety":[129],"at":[130],"both":[131],"local":[132],"global":[134],"scales.":[135],"The":[136],"experimental":[137],"results":[138],"demonstrate":[139],"R3S":[141],"improves":[142],"accuracy":[144],"efficiently":[149],"harmonizes":[150],"heterogeneous":[152],"preferences":[153],"users.":[156]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}