{"id":"https://openalex.org/W4223629561","doi":"https://doi.org/10.1145/3624918.3625311","title":"Reinforcement Re-ranking with 2D Grid-based Recommendation Panels","display_name":"Reinforcement Re-ranking with 2D Grid-based Recommendation Panels","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4223629561","doi":"https://doi.org/10.1145/3624918.3625311"},"language":"en","primary_location":{"id":"doi:10.1145/3624918.3625311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624918.3625311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.04954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073327702","display_name":"Sirui Chen","orcid":"https://orcid.org/0000-0001-7740-508X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sirui Chen","raw_affiliation_strings":["School of Information, Renmin University of China, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320847","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0001-7397-5632"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Gaoling School of AI (GSAI), Renmin University of China, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of AI (GSAI), Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Gaoling School of AI (GSAI), Renmin University of China, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of AI (GSAI), Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390297","display_name":"Zhiyu Li","orcid":"https://orcid.org/0009-0008-3196-7739"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Li","raw_affiliation_strings":["Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101336430","display_name":"Yuan Wang","orcid":"https://orcid.org/0000-0002-3630-9179"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Wang","raw_affiliation_strings":["Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763939","display_name":"Quan Lin","orcid":"https://orcid.org/0009-0002-7149-5525"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Lin","raw_affiliation_strings":["Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of AI (GSAI), Renmin University of China, China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of AI (GSAI), Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073327702"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":1.3699,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83342529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"282","last_page":"287"},"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":0.9977999925613403,"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":0.9690999984741211,"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/ranking","display_name":"Ranking (information retrieval)","score":0.8839340209960938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8016660809516907},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7719669342041016},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.7243825197219849},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6639403104782104},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6443750262260437},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5181704759597778},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5033380389213562},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4385189116001129},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.4287586510181427},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4035886824131012},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38817763328552246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3786843419075012},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35516834259033203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07268613576889038},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06376922130584717}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8839340209960938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016660809516907},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7719669342041016},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.7243825197219849},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6639403104782104},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6443750262260437},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5181704759597778},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5033380389213562},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4385189116001129},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.4287586510181427},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4035886824131012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38817763328552246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3786843419075012},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35516834259033203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07268613576889038},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06376922130584717},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3624918.3625311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624918.3625311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.04954","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.04954","pdf_url":"https://arxiv.org/pdf/2204.04954","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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:2204.04954","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.04954","pdf_url":"https://arxiv.org/pdf/2204.04954","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2020067207","https://openalex.org/W2042998450","https://openalex.org/W2138108551","https://openalex.org/W2736601468","https://openalex.org/W2739826497","https://openalex.org/W2739860611","https://openalex.org/W2788079612","https://openalex.org/W2799544270","https://openalex.org/W2894741346","https://openalex.org/W2912938607","https://openalex.org/W2914121279","https://openalex.org/W2953132212","https://openalex.org/W2963842088","https://openalex.org/W2963864421","https://openalex.org/W2964032749","https://openalex.org/W2973171206","https://openalex.org/W2996959725","https://openalex.org/W3035106673","https://openalex.org/W3080913646","https://openalex.org/W3102899483","https://openalex.org/W3113470404","https://openalex.org/W3116873649","https://openalex.org/W4379914435","https://openalex.org/W4380136520","https://openalex.org/W4385567603"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W2922107804","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Modern":[0],"recommender":[1,52,131],"systems":[2,53],"usually":[3],"present":[4],"items":[5,22,35,43,118],"as":[6,137,148,159,170],"a":[7,15,68,109,210,256,260],"streaming,":[8],"one-dimensional":[9],"ranking":[10,143,165,201],"list.":[11],"Recently":[12],"there":[13],"is":[14,203,225,241],"trend":[16],"in":[17,36,44,67,119,162,198,249,269],"e-commerce":[18,262],"that":[19],"the":[20,34,65,77,87,90,100,117,125,130,145,149,154,160,163,168,171,174,178,181,195,199,206,214,220,230,247,250,265],"recommended":[21],"are":[23,57,233],"organized":[24],"grid-based":[25,45,69,95,121,274],"panels":[26,47,96,123],"with":[27],"two":[28,190],"dimensions":[29],"where":[30],"users":[31],"can":[32],"view":[33],"both":[37],"vertical":[38],"and":[39,97,167,177,245,253],"horizontal":[40],"directions.":[41],"Presenting":[42],"result":[46,122,275],"poses":[48],"new":[49],"challenges":[50],"to":[51,60,115,136,243],"because":[54],"existing":[55],"models":[56],"all":[58,228],"designed":[59],"output":[61],"sequential":[62],"lists":[63],"while":[64],"slots":[66,232],"panel":[70,231],"have":[71],"no":[72],"explicit":[73],"order.":[74],"Directly":[75],"converting":[76],"item":[78,142,197,215,221],"rankings":[79],"into":[80],"grids":[81],"(e.g.,":[82],"pre-defining":[83],"an":[84,140],"order":[85],"on":[86,94,255],"slots)":[88],"overlooks":[89],"user-specific":[91],"behavioral":[92],"patterns":[93],"inevitably":[98],"hurts":[99],"user":[101],"experiences.":[102],"To":[103],"address":[104],"this":[105],"issue,":[106],"we":[107],"propose":[108],"novel":[110],"Markov":[111],"decision":[112],"process":[113,224],"(MDP)":[114],"place":[116],"2D":[120,273],"at":[124],"final":[126],"re-ranking":[127],"stage":[128],"of":[129,173,180,229,239,267,271],"systems.":[132],"The":[133,223,235],"model,":[134],"referred":[135],"Panel-MDP,":[138],"takes":[139],"initial":[141,164,200],"from":[144,259],"early":[146],"stages":[147],"input.":[150],"Then,":[151],"it":[152],"defines":[153],"MDP":[155],"discrete":[156],"time":[157,185],"steps":[158],"ranks":[161],"list,":[166],"actions":[169],"prediction":[172],"user-item":[175],"preference":[176],"selection":[179],"slots.":[182],"At":[183],"each":[184],"step,":[186],"Panel-MDP":[187,268],"sequentially":[188],"executes":[189],"sub-actions:":[191],"first":[192],"deciding":[193],"whether":[194],"current":[196],"list":[202],"preferred":[204],"by":[205],"user;":[207],"then":[208],"selecting":[209],"slot":[211],"for":[212],"placing":[213],"if":[216],"preferred,":[217],"or":[218],"skipping":[219],"otherwise.":[222],"continued":[226],"until":[227],"filled.":[234],"reinforcement":[236],"learning":[237],"algorithm":[238],"PPO":[240],"employed":[242],"implement":[244],"learn":[246],"parameters":[248],"Panel-MDP.":[251],"Simulation":[252],"experiments":[254],"dataset":[257],"collected":[258],"widely-used":[261],"app":[263],"demonstrated":[264],"superiority":[266],"terms":[270],"recommending":[272],"panels.":[276]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}