{"id":"https://openalex.org/W4384648944","doi":"https://doi.org/10.1145/3539618.3591899","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","display_name":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384648944","doi":"https://doi.org/10.1145/3539618.3591899"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591899","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":"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/A5008534055","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-7767-2329"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Wang","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016593216","display_name":"Zhene Zou","orcid":"https://orcid.org/0009-0002-0142-1010"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhene Zou","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597607","display_name":"Minghao Zhao","orcid":"https://orcid.org/0000-0003-2871-0023"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Zhao","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778581","display_name":"Qilin Deng","orcid":"https://orcid.org/0000-0002-0506-5511"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilin Deng","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007766416","display_name":"\u60a6\u96c4 \u6c34\u4e0a","orcid":"https://orcid.org/0000-0001-9842-9937"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Shang","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103034185","display_name":"Yile Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yile Liang","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069512988","display_name":"Runze Wu","orcid":"https://orcid.org/0000-0002-6986-5825"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Wu","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102027521","display_name":"Xudong Shen","orcid":"https://orcid.org/0000-0003-0447-2614"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Shen","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112845879","display_name":"Tangjie Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tangjie Lyu","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022008180","display_name":"Changjie Fan","orcid":"https://orcid.org/0000-0001-5420-0516"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjie Fan","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5008534055"],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":6.3931,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96615938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2935","last_page":"2944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9901999831199646,"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":0.9848999977111816,"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":0.8933429718017578},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8618400692939758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8392539024353027},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.8231086730957031},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6300589442253113},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5510778427124023},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5162741541862488},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5059384703636169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4747886061668396},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47477197647094727},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11641237139701843}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8933429718017578},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8618400692939758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8392539024353027},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.8231086730957031},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6300589442253113},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5510778427124023},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5162741541862488},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5059384703636169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747886061668396},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47477197647094727},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11641237139701843},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591899","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591899","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2155027007","https://openalex.org/W2234859443","https://openalex.org/W2260756217","https://openalex.org/W2262817822","https://openalex.org/W2340679559","https://openalex.org/W2475334473","https://openalex.org/W2761873684","https://openalex.org/W2787933113","https://openalex.org/W2787938642","https://openalex.org/W2811374584","https://openalex.org/W2886601525","https://openalex.org/W2898621204","https://openalex.org/W2902572901","https://openalex.org/W2904453761","https://openalex.org/W2916086000","https://openalex.org/W2919013397","https://openalex.org/W2946327583","https://openalex.org/W2948345531","https://openalex.org/W2962745591","https://openalex.org/W2963654596","https://openalex.org/W2964108915","https://openalex.org/W2984869362","https://openalex.org/W3033324992","https://openalex.org/W3116566929","https://openalex.org/W3130177876","https://openalex.org/W3183218305","https://openalex.org/W3201178526","https://openalex.org/W4233471163","https://openalex.org/W6630221451","https://openalex.org/W6777656069"],"related_works":["https://openalex.org/W2968745142","https://openalex.org/W2809363009","https://openalex.org/W2348159088","https://openalex.org/W2045871438","https://openalex.org/W4296555327","https://openalex.org/W4384648944","https://openalex.org/W2743342830","https://openalex.org/W4286901590","https://openalex.org/W3205450119","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,9],"based":[2],"recommender":[3],"systems":[4],"(RL-based":[5],"RS)":[6],"aim":[7],"at":[8,154],"a":[10,14,33,90,116],"good":[11],"policy":[12,105,145],"from":[13,78],"batch":[15,140],"of":[16,66,81,97],"collected":[17],"data,":[18],"by":[19],"casting":[20],"recommendations":[21],"to":[22,49,62,88],"multi-step":[23],"decision-making":[24],"tasks.":[25],"However,":[26],"current":[27],"RL-based":[28,68,75],"RS":[29,56,69,76],"research":[30],"commonly":[31],"has":[32],"large":[34],"reality":[35,124],"gap.":[36],"In":[37,107],"this":[38],"paper,":[39],"we":[40],"introduce":[41],"the":[42,51,63,67,79,109,123],"first":[43],"open-source":[44],"real-world":[45,128],"dataset,":[46],"RL4RS,":[47],"hoping":[48],"replace":[50],"artificial":[52],"datasets":[53,57],"and":[54,103,143],"semi-simulated":[55],"previous":[58],"studies":[59],"used":[60],"due":[61],"resource":[64,118],"limitation":[65],"domain.":[70],"Unlike":[71],"academic":[72],"RL":[73,138,141],"research,":[74],"suffers":[77],"difficulties":[80],"being":[82],"well-validated":[83],"before":[84],"deployment.":[85],"We":[86],"attempt":[87],"propose":[89],"new":[91,117],"systematic":[92],"evaluation":[93,96,100,146],"framework,":[94],"including":[95],"environment":[98],"simulation,":[99],"on":[101,122],"environments,":[102,135],"counterfactual":[104,144],"evaluation.":[106],"summary,":[108],"RL4RS":[110,149],"(Reinforcement":[111],"Learning":[112],"for":[113],"Recommender":[114],"Systems),":[115],"with":[119],"special":[120],"concerns":[121],"gaps,":[125],"contains":[126],"two":[127],"datasets,":[129],"data":[130],"understanding":[131],"tools,":[132],"tuned":[133],"simulation":[134],"related":[136],"advanced":[137],"baselines,":[139,142],"algorithms.":[147],"The":[148],"suite":[150],"can":[151],"be":[152],"found":[153],"https://github.com/fuxiAIlab/RL4RS.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}