{"id":"https://openalex.org/W4395445743","doi":"https://doi.org/10.1145/3659947","title":"M <sup>3</sup> Rec: A Context-Aware Offline Meta-Level Model-Based Reinforcement Learning Approach for Cold-Start Recommendation","display_name":"M <sup>3</sup> Rec: A Context-Aware Offline Meta-Level Model-Based Reinforcement Learning Approach for Cold-Start Recommendation","publication_year":2024,"publication_date":"2024-04-25","ids":{"openalex":"https://openalex.org/W4395445743","doi":"https://doi.org/10.1145/3659947"},"language":"en","primary_location":{"id":"doi:10.1145/3659947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659947","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3659947","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039956108","display_name":"Yanan Wang","orcid":"https://orcid.org/0009-0008-1301-0159"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanan Wang","raw_affiliation_strings":["University of Arizona, Tucson, AZ, USA"],"raw_orcid":"https://orcid.org/0009-0008-1301-0159","affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050609316","display_name":"Yong Ge","orcid":"https://orcid.org/0000-0002-9630-795X"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Ge","raw_affiliation_strings":["University of Arizona, Tucson, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-9630-795X","affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026341901","display_name":"Zhepeng Li","orcid":"https://orcid.org/0000-0002-7988-0412"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhepeng Li","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7988-0412","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361140","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-3365-8904"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Samsung Research America, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3365-8904","affiliations":[{"raw_affiliation_string":"Samsung Research America, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004491098","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-8161-7365"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["Samsung Research America, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8161-7365","affiliations":[{"raw_affiliation_string":"Samsung Research America, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.554,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90852926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"42","issue":"6","first_page":"1","last_page":"27"},"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":0.9987999796867371,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9455000162124634,"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":0.7797198295593262},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6673409938812256},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5363517999649048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4951423704624176},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4431923031806946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3616648018360138},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20548468828201294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17329025268554688},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.09636199474334717},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07287648320198059},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07038304209709167}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7797198295593262},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6673409938812256},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5363517999649048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4951423704624176},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4431923031806946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3616648018360138},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20548468828201294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17329025268554688},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.09636199474334717},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07287648320198059},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07038304209709167},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3659947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659947","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:hub.hku.hk:10722/347617","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/347617","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3659947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3659947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3659947","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2470902905","display_name":"III: Small: Collaborative Research: Harnessing Big Data for Improving Career Mobility","funder_award_id":"2007437","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G365062286","display_name":"CAREER: Mining Career, Education and Job Data to Bridge the Talent Gap between Demand and Supply","funder_award_id":"1844983","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395445743.pdf","grobid_xml":"https://content.openalex.org/works/W4395445743.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W166862392","https://openalex.org/W1532325895","https://openalex.org/W1999874108","https://openalex.org/W2064675550","https://openalex.org/W2073021764","https://openalex.org/W2119717200","https://openalex.org/W2123399796","https://openalex.org/W2198041288","https://openalex.org/W2219888463","https://openalex.org/W2419501139","https://openalex.org/W2605350416","https://openalex.org/W2625746539","https://openalex.org/W2739805805","https://openalex.org/W2788295351","https://openalex.org/W2902572901","https://openalex.org/W2948345531","https://openalex.org/W2962872206","https://openalex.org/W2964983698","https://openalex.org/W2965512832","https://openalex.org/W2984100107","https://openalex.org/W3012881846","https://openalex.org/W3031596603","https://openalex.org/W3034853385","https://openalex.org/W3043239945","https://openalex.org/W3081320135","https://openalex.org/W3098231197","https://openalex.org/W3102778384","https://openalex.org/W3123956618","https://openalex.org/W3173984942","https://openalex.org/W3187977559","https://openalex.org/W3188301284","https://openalex.org/W3195061894","https://openalex.org/W3206310679","https://openalex.org/W4205513846","https://openalex.org/W4226072877","https://openalex.org/W4282567554","https://openalex.org/W4283070072","https://openalex.org/W4296604485","https://openalex.org/W4306316975","https://openalex.org/W4384891727","https://openalex.org/W4385275467","https://openalex.org/W6601247122","https://openalex.org/W6732103282"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,193],"(RL)":[2],"has":[3],"shown":[4],"great":[5],"promise":[6],"in":[7,12,54,62],"optimizing":[8],"long-term":[9],"user":[10,28,78,91,118,178],"interest":[11],"recommender":[13,65],"systems.":[14],"However,":[15],"existing":[16],"RL-based":[17,64],"recommendation":[18,32,96,142,181,213],"methods":[19],"need":[20,147],"a":[21,46,69,90,140,172,208],"large":[22],"number":[23,48],"of":[24,49,139,166,188,211],"interactions":[25],"for":[26,77,148],"each":[27,86],"to":[29,41,84,98,101,115,135,162,197],"learn":[30],"the":[31,59,63,117,137,146,151,164,177,186,212],"policy.":[33],"The":[34],"challenge":[35,61,165],"becomes":[36],"more":[37],"critical":[38],"when":[39,195],"recommending":[40],"new":[42,102,198],"users":[43,103,199],"who":[44],"have":[45],"limited":[47,105,124,201],"interactions.":[50],"To":[51,108,144],"that":[52,94],"end,":[53],"this":[55],"article,":[56],"we":[57,170,206],"address":[58],"cold-start":[60],"systems":[66,97],"by":[67],"proposing":[68],"novel":[70],"context-aware":[71],"offline":[72,159,167,191],"meta-level":[73,141],"model-based":[74],"RL":[75,130],"approach":[76,82,113],"adaptation.":[79],"Our":[80],"proposed":[81,152],"learns":[83,114],"infer":[85],"user's":[87],"preference":[88],"with":[89,104,200],"context":[92],"variable":[93],"enables":[95],"better":[99],"adapt":[100],"contextual":[106,125,202],"information.":[107,203],"improve":[109],"adaptation":[110],"efficiency,":[111],"our":[112,189],"recover":[116],"choice":[119],"function":[120],"and":[121,180],"reward":[122],"from":[123],"information":[126,174],"through":[127],"an":[128],"inverse":[129],"method,":[131],"which":[132],"is":[133,154],"used":[134],"assist":[136],"training":[138],"agent.":[143,182],"avoid":[145],"online":[149],"interaction,":[150],"method":[153,194],"trained":[155],"using":[156],"historically":[157],"collected":[158],"data.":[160],"Moreover,":[161],"tackle":[163],"policy":[168,192],"training,":[169],"introduce":[171],"mutual":[173],"constraint":[175],"between":[176],"model":[179],"Evaluation":[183],"results":[184],"show":[185],"superiority":[187],"developed":[190],"adapting":[196],"In":[204],"addition,":[205],"provide":[207],"theoretical":[209],"analysis":[210],"performance":[214],"bound.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}