{"id":"https://openalex.org/W3087898974","doi":"https://doi.org/10.1145/3383313.3412233","title":"Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication","display_name":"Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication","publication_year":2020,"publication_date":"2020-09-19","ids":{"openalex":"https://openalex.org/W3087898974","doi":"https://doi.org/10.1145/3383313.3412233","mag":"3087898974"},"language":"en","primary_location":{"id":"doi:10.1145/3383313.3412233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383313.3412233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourteenth ACM Conference on Recommender Systems","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/A5102854756","display_name":"Xu He","orcid":"https://orcid.org/0000-0002-7700-2341"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xu HE","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["School of Computer Science and Engineering Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047241706","display_name":"Yanghua Li","orcid":"https://orcid.org/0000-0001-9072-435X"},"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":"Yanghua Li","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089649988","display_name":"Haikai Chen","orcid":null},"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":"Haikai Chen","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023750802","display_name":"Rundong Wang","orcid":"https://orcid.org/0000-0001-6237-9472"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rundong Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049783685","display_name":"Xinrun Wang","orcid":"https://orcid.org/0000-0003-3369-219X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinrun Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552914","display_name":"Runsheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Runsheng Yu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353780","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0041-3134"},"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":"Xin Li","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113908133","display_name":"Zhirong Wang","orcid":null},"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":"Zhirong Wang","raw_affiliation_strings":["Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2498,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93514761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9972000122070312,"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/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8368113040924072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531828880310059},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5217329263687134},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43655872344970703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3290242552757263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13831883668899536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8368113040924072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531828880310059},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5217329263687134},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43655872344970703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3290242552757263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13831883668899536},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3383313.3412233","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383313.3412233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fourteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2112794046","https://openalex.org/W2341234495","https://openalex.org/W2617547828","https://openalex.org/W2781726626","https://openalex.org/W2787933113","https://openalex.org/W2794643322","https://openalex.org/W2797234205","https://openalex.org/W2798835721","https://openalex.org/W2799544270","https://openalex.org/W2804766086","https://openalex.org/W2808227867","https://openalex.org/W2912454685","https://openalex.org/W2963842088","https://openalex.org/W3098283217","https://openalex.org/W3102899483","https://openalex.org/W3103497827","https://openalex.org/W4231934124","https://openalex.org/W6631834165"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"With":[0],"the":[1,67,71,90,136,146],"rise":[2],"of":[3,39,46,70,121,135,145],"online":[4,19],"e-commerce":[5,155],"platforms,":[6],"more":[7,9,17],"and":[8,54],"customers":[10],"prefer":[11],"to":[12,24,118,141],"shop":[13],"online.":[14],"To":[15],"sell":[16],"products,":[18],"platforms":[20],"introduce":[21],"various":[22],"modules":[23,48,94,123],"recommend":[25],"items":[26],"with":[27,89],"different":[28,40,52,93,129],"properties":[29],"such":[30],"as":[31],"huge":[32],"discounts.":[33],"A":[34],"web":[35],"page":[36,73],"often":[37],"consists":[38],"independent":[41],"modules.":[42,65,130],"The":[43],"ranking":[44],"policies":[45],"these":[47],"are":[49,99],"decided":[50],"by":[51,103,124],"teams":[53],"optimized":[55],"individually":[56],"without":[57],"cooperation,":[58],"which":[59],"might":[60],"result":[61],"in":[62,107],"competition":[63],"between":[64],"Thus,":[66],"global":[68,148],"policy":[69],"whole":[72],"could":[74],"be":[75],"sub-optimal.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,113],"propose":[81],"a":[82,104,115],"novel":[83],"multi-agent":[84],"cooperative":[85],"reinforcement":[86],"learning":[87],"approach":[88],"restriction":[91],"that":[92,158],"cannot":[95],"communicate.":[96],"Our":[97],"contributions":[98],"three-fold.":[100],"Firstly,":[101],"inspired":[102],"solution":[105],"concept":[106],"game":[108],"theory":[109],"named":[110],"correlated":[111],"equilibrium,":[112],"design":[114],"signal":[116,137],"network":[117,138],"promote":[119],"cooperation":[120],"all":[122],"generating":[125],"signals":[126],"(vectors)":[127],"for":[128],"Secondly,":[131],"an":[132],"entropy-regularized":[133],"version":[134],"is":[139],"proposed":[140],"coordinate":[142],"agents\u2019":[143],"exploration":[144],"optimal":[147],"policy.":[149],"Furthermore,":[150],"experiments":[151],"based":[152],"on":[153],"real-world":[154],"data":[156],"demonstrate":[157],"our":[159],"algorithm":[160],"obtains":[161],"superior":[162],"performance":[163],"over":[164],"baselines.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}