{"id":"https://openalex.org/W4384652161","doi":"https://doi.org/10.1145/3539618.3591656","title":"Contrastive State Augmentations for Reinforcement Learning-Based Recommender Systems","display_name":"Contrastive State Augmentations for Reinforcement Learning-Based Recommender Systems","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384652161","doi":"https://doi.org/10.1145/3539618.3591656"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591656","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th 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":"green","oa_url":"https://eprints.gla.ac.uk/view/author/7010.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100384130","display_name":"Zhaochun Ren","orcid":"https://orcid.org/0000-0002-9076-6565"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaochun Ren","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-9076-6565","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026823811","display_name":"Na Huang","orcid":"https://orcid.org/0009-0003-3844-3237"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Huang","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0003-3844-3237","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045200779","display_name":"Yidan Wang","orcid":"https://orcid.org/0009-0002-5772-5910"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Wang","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0002-5772-5910","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046700486","display_name":"Pengjie Ren","orcid":"https://orcid.org/0000-0003-2964-6422"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Ren","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-2964-6422","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643097","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0003-0203-4610"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0203-4610","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035640074","display_name":"Jiahuan Lei","orcid":"https://orcid.org/0000-0002-5170-8645"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahuan Lei","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5170-8645","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014964385","display_name":"Xinlei Shi","orcid":"https://orcid.org/0000-0002-0733-5757"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlei Shi","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0733-5757","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014828450","display_name":"Hengliang Luo","orcid":"https://orcid.org/0000-0001-8597-8873"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengliang Luo","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8597-8873","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","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 Jose","raw_affiliation_strings":["University of Glasgow, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9228-1759","affiliations":[{"raw_affiliation_string":"University of Glasgow, London, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393241","display_name":"Xin Xin","orcid":"https://orcid.org/0000-0001-6116-9115"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xin","raw_affiliation_strings":["Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6116-9115","affiliations":[{"raw_affiliation_string":"Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"922","last_page":"931"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9641000032424927,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9315688014030457},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8340532779693604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8230632543563843},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.505730390548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49623018503189087},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4949721693992615},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4820612072944641},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4545724093914032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4312414824962616},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3462459444999695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07226380705833435}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9315688014030457},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8340532779693604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230632543563843},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.505730390548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49623018503189087},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4949721693992615},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4820612072944641},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4545724093914032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4312414824962616},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3462459444999695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07226380705833435},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3591656","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:299230","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/7010.html>","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":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:299230","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/7010.html>","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":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2003888216","display_name":null,"funder_award_id":"ZR2021QF129","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G394483262","display_name":"\u57fa\u4e8e\u591a\u6e90\u5f02\u6784\u6570\u636e\u878d\u5408\u7684\u53ef\u89e3\u91ca\u6027\u533b\u7597\u5065\u5eb7\u95ee\u7b54\u6280\u672f\u7814\u7a76","funder_award_id":"61972234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4890194082","display_name":null,"funder_award_id":"2020QNQT017","funder_id":"https://openalex.org/F4320311026","funder_display_name":"Shandong University"},{"id":"https://openalex.org/G69085316","display_name":null,"funder_award_id":"62102234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8283770779","display_name":null,"funder_award_id":"62272274","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G83507391","display_name":null,"funder_award_id":"62202271","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8672301212","display_name":"\u9762\u5411\u4e3b\u8981\u4f9d\u636e\u9690\u53cd\u9988\u6570\u636e\u7684\u4f1a\u8bdd\u578b\u63a8\u8350\u7cfb\u7edf\u53ca\u529f\u80fd\u589e\u5f3a\u7814\u7a76","funder_award_id":"62072279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2121720950","https://openalex.org/W2135598826","https://openalex.org/W2171279286","https://openalex.org/W2295739661","https://openalex.org/W2510184840","https://openalex.org/W2512965516","https://openalex.org/W2625746539","https://openalex.org/W2783272285","https://openalex.org/W2788295351","https://openalex.org/W2790523245","https://openalex.org/W2799544270","https://openalex.org/W2902040508","https://openalex.org/W2963367478","https://openalex.org/W2963601856","https://openalex.org/W2963842088","https://openalex.org/W2984100107","https://openalex.org/W2989395196","https://openalex.org/W2996959725","https://openalex.org/W3034853385","https://openalex.org/W3094605801","https://openalex.org/W3098231197","https://openalex.org/W3102778384","https://openalex.org/W3102899483","https://openalex.org/W3133849783","https://openalex.org/W3153325943","https://openalex.org/W3173365306","https://openalex.org/W3173984942","https://openalex.org/W3206127589","https://openalex.org/W3206324923","https://openalex.org/W4283796596","https://openalex.org/W4361230837"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W4310083477","https://openalex.org/W3092950680","https://openalex.org/W4246980185","https://openalex.org/W2150182025","https://openalex.org/W3197542405","https://openalex.org/W2418190244","https://openalex.org/W4238861846"],"abstract_inverted_index":{"Learning":[0],"reinforcement":[1],"learning":[2],"(RL)-based":[3],"recommenders":[4],"from":[5,52],"historical":[6],"user-item":[7],"interaction":[8],"sequences":[9],"is":[10],"vital":[11],"to":[12,29,47,57],"generate":[13],"high-reward":[14],"recommendations":[15],"and":[16,45],"improve":[17],"long-term":[18],"cumulative":[19],"benefits.":[20],"However,":[21],"existing":[22],"RL":[23],"recommendation":[24],"methods":[25],"encounter":[26],"difficulties":[27],"(i)":[28],"estimate":[30],"the":[31,41,58],"value":[32],"functions":[33],"for":[34],"states":[35],"which":[36],"are":[37],"not":[38],"contained":[39],"in":[40],"offline":[42],"training":[43],"data,":[44],"(ii)":[46],"learn":[48],"effective":[49],"state":[50],"representations":[51],"user":[53],"implicit":[54],"feedback":[55],"due":[56],"lack":[59],"of":[60],"contrastive":[61],"signals.":[62]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
