{"id":"https://openalex.org/W4386728814","doi":"https://doi.org/10.1145/3604915.3608843","title":"Scalable Deep Q-Learning for Session-Based Slate Recommendation","display_name":"Scalable Deep Q-Learning for Session-Based Slate Recommendation","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4386728814","doi":"https://doi.org/10.1145/3604915.3608843"},"language":"en","primary_location":{"id":"doi:10.1145/3604915.3608843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604915.3608843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604915.3608843","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3604915.3608843","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002049317","display_name":"Aayush Singha Roy","orcid":"https://orcid.org/0009-0000-7085-3306"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Aayush Singha Roy","raw_affiliation_strings":["Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics,, Ireland"],"raw_orcid":"https://orcid.org/0009-0000-7085-3306","affiliations":[{"raw_affiliation_string":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics,, Ireland","institution_ids":["https://openalex.org/I42934936","https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020252920","display_name":"Edoardo D\u2019Amico","orcid":"https://orcid.org/0000-0002-8262-7207"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Edoardo D'Amico","raw_affiliation_strings":["Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-8262-7207","affiliations":[{"raw_affiliation_string":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038973041","display_name":"\u0397\u03bb\u03af\u03b1\u03c2 \u03a4\u03c1\u03ac\u03b3\u03bf\u03c2","orcid":"https://orcid.org/0000-0001-9566-531X"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Elias Tragos","raw_affiliation_strings":["Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9566-531X","affiliations":[{"raw_affiliation_string":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079971230","display_name":"Aonghus Lawlor","orcid":"https://orcid.org/0000-0002-6160-4639"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Aonghus Lawlor","raw_affiliation_strings":["Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-6160-4639","affiliations":[{"raw_affiliation_string":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084111561","display_name":"Neil Hurley","orcid":"https://orcid.org/0000-0001-8428-2866"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Neil Hurley","raw_affiliation_strings":["Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics,, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-8428-2866","affiliations":[{"raw_affiliation_string":"Computer Science, University College Dublin, Ireland and Insight Centre for Data Analytics,, Ireland","institution_ids":["https://openalex.org/I42934936","https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002049317"],"corresponding_institution_ids":["https://openalex.org/I100930933","https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":1.7937,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88389749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"877","last_page":"882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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":0.9944000244140625,"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":0.8450789451599121},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.8079880475997925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992754578590393},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.776196300983429},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7041239738464355},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5689545273780823},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5525290966033936},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5469583868980408},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5424339175224304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5081877708435059},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45373740792274475},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4429120421409607},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42727792263031006},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.136962890625},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.134816974401474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11894375085830688},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11503183841705322}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8450789451599121},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.8079880475997925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992754578590393},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.776196300983429},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7041239738464355},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5689545273780823},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5525290966033936},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5469583868980408},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5424339175224304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081877708435059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45373740792274475},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4429120421409607},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42727792263031006},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.136962890625},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.134816974401474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11894375085830688},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11503183841705322},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604915.3608843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604915.3608843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604915.3608843","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3604915.3608843","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604915.3608843","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604915.3608843","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1383882326","display_name":null,"funder_award_id":"SFI/12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2632164605","display_name":null,"funder_award_id":"SFI/12/RC/2289_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3259019331","display_name":null,"funder_award_id":"12/RC/2289_P2","funder_id":"https://openalex.org/F4320331354","funder_display_name":"Insight SFI Research Centre for Data Analytics"},{"id":"https://openalex.org/G3695527833","display_name":null,"funder_award_id":"12/RC/2289_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G5098725405","display_name":null,"funder_award_id":"12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7988105472","display_name":null,"funder_award_id":"SFI/12/RC/2289_P2","funder_id":"https://openalex.org/F4320331354","funder_display_name":"Insight SFI Research Centre for Data Analytics"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320331354","display_name":"Insight SFI Research Centre for Data Analytics","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386728814.pdf","grobid_xml":"https://content.openalex.org/works/W4386728814.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2210543184","https://openalex.org/W2902572901","https://openalex.org/W2914639375","https://openalex.org/W2946327583","https://openalex.org/W3123348991","https://openalex.org/W3210174084","https://openalex.org/W4241087722","https://openalex.org/W4296604407","https://openalex.org/W4317837964","https://openalex.org/W4377018833"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W2625725254","https://openalex.org/W2563912921"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"demonstrated":[4],"great":[5],"potential":[6],"to":[7,71,76,126,158],"improve":[8],"slate-based":[9],"recommender":[10],"systems":[11],"by":[12,169],"optimizing":[13],"recommendations":[14],"for":[15],"long-term":[16],"user":[17,155],"engagement.":[18],"To":[19,110],"handle":[20],"the":[21,31,45,49,77,93,97,121,124,165],"combinatorial":[22],"action":[23,59],"space":[24],"in":[25,63,139],"slate":[26,35,166],"recommendation,":[27],"recent":[28],"works":[29],"decompose":[30],"Q-value":[32],"of":[33,68,79,96,123,129],"a":[34,53,64,127,159],"into":[36],"item-wise":[37,41],"Q-values,":[38],"using":[39],"an":[40,73,116],"value-based":[42,160],"policy.":[43],"However,":[44],"common":[46],"case":[47],"where":[48],"value":[50],"function":[51,55],"is":[52],"parameterized":[54,98],"taking":[56],"state":[57],"and":[58,135],"as":[60,101],"input":[61],"results":[62],"linearly":[65],"increasing":[66],"number":[67,78],"evaluations":[69],"required":[70],"select":[72],"action,":[74],"proportional":[75],"candidate":[80],"items.":[81],"While":[82],"slow":[83],"training":[84],"may":[85],"be":[86],"acceptable,":[87],"this":[88,112],"becomes":[89],"intractable":[90],"when":[91],"considering":[92],"costly":[94],"evaluation":[95,122],"function,":[99],"such":[100],"with":[102],"deep":[103],"neural":[104],"networks,":[105],"during":[106],"model":[107],"serving":[108,167],"time.":[109],"address":[111],"issue,":[113],"we":[114,147],"propose":[115],"actor-based":[117],"policy":[118],"that":[119,149],"reduces":[120],"Q-function":[125],"subset":[128],"items,":[130],"significantly":[131,163],"reducing":[132,164],"inference":[133],"time":[134,168],"enabling":[136],"practical":[137],"deployment":[138],"real-world":[140],"industrial":[141],"settings.":[142],"In":[143],"our":[144,150],"empirical":[145],"evaluation,":[146],"demonstrate":[148],"proposed":[151],"approach":[152],"achieves":[153],"equivalent":[154],"session":[156],"engagement":[157],"policy,":[161],"while":[162],"at":[170],"least":[171],"4":[172],"times.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}