{"id":"https://openalex.org/W2963440040","doi":"https://doi.org/10.1145/3178876.3186039","title":"Reinforcement Mechanism Design for e-commerce","display_name":"Reinforcement Mechanism Design for e-commerce","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2963440040","doi":"https://doi.org/10.1145/3178876.3186039","mag":"2963440040"},"language":"en","primary_location":{"id":"doi:10.1145/3178876.3186039","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186039","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186039&type=pdf","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 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3186039&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016589992","display_name":"Qingpeng Cai","orcid":"https://orcid.org/0000-0001-6451-9299"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingpeng Cai","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065488177","display_name":"Aris Filos-Ratsikas","orcid":"https://orcid.org/0000-0001-7868-8114"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aris Filos-Ratsikas","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013558969","display_name":"Pingzhong Tang","orcid":"https://orcid.org/0000-0003-1330-1999"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingzhong Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100410215","display_name":"Yiwei Zhang","orcid":"https://orcid.org/0000-0002-3499-9911"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwei Zhang","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.6503,"has_fulltext":true,"cited_by_count":84,"citation_normalized_percentile":{"value":0.98944854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1339","last_page":"1348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994000196456909,"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":0.9977999925613403,"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":0.7914983034133911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733944296836853},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5999075174331665},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5621530413627625},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5206626653671265},{"id":"https://openalex.org/keywords/sophistication","display_name":"Sophistication","score":0.4809762239456177},{"id":"https://openalex.org/keywords/mechanism-design","display_name":"Mechanism design","score":0.44662293791770935},{"id":"https://openalex.org/keywords/e-commerce","display_name":"E-commerce","score":0.4272632300853729},{"id":"https://openalex.org/keywords/revenue","display_name":"Revenue","score":0.4236640930175781},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41886264085769653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37999990582466125},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3197062611579895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23898959159851074},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.1885305941104889},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11470493674278259},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10924044251441956}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7914983034133911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733944296836853},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5999075174331665},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5621530413627625},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5206626653671265},{"id":"https://openalex.org/C168725872","wikidata":"https://www.wikidata.org/wiki/Q991663","display_name":"Sophistication","level":2,"score":0.4809762239456177},{"id":"https://openalex.org/C153517567","wikidata":"https://www.wikidata.org/wiki/Q26090","display_name":"Mechanism design","level":2,"score":0.44662293791770935},{"id":"https://openalex.org/C78597825","wikidata":"https://www.wikidata.org/wiki/Q484847","display_name":"E-commerce","level":2,"score":0.4272632300853729},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.4236640930175781},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41886264085769653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37999990582466125},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3197062611579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23898959159851074},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.1885305941104889},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11470493674278259},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10924044251441956},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3178876.3186039","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186039","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186039&type=pdf","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 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/0d7fd3c9-eacb-4e02-a1b9-5b2a33f57228","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0d7fd3c9-eacb-4e02-a1b9-5b2a33f57228","pdf_url":"https://www.research.ed.ac.uk/files/296358239/Reinforcement_Mechanism_CAI_DOA22122017_VOR_CC_BY.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cai, Q, Filos-Ratsikas, A, Tang, P & Zhang, Y 2018, Reinforcement Mechanism Design for E-Commerce. in Proceedings of the 2018 World Wide Web Conference. WWW '18, pp. 1339\u20131348, The Web Conference 2018, Lyon, France, 23/04/18. https://doi.org/10.1145/3178876.3186039","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3178876.3186039","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186039","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186039&type=pdf","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 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6424090627","display_name":null,"funder_award_id":"61561146398","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963440040.pdf","grobid_xml":"https://content.openalex.org/works/W2963440040.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W116854235","https://openalex.org/W1486317198","https://openalex.org/W1539297723","https://openalex.org/W1690919088","https://openalex.org/W1757796397","https://openalex.org/W1978260564","https://openalex.org/W1982262386","https://openalex.org/W1988790447","https://openalex.org/W2000080679","https://openalex.org/W2024390895","https://openalex.org/W2072459156","https://openalex.org/W2077902449","https://openalex.org/W2100677568","https://openalex.org/W2109826765","https://openalex.org/W2111241577","https://openalex.org/W2112420033","https://openalex.org/W2116067849","https://openalex.org/W2126776273","https://openalex.org/W2136602922","https://openalex.org/W2138634621","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2165150801","https://openalex.org/W2166253248","https://openalex.org/W2168405694","https://openalex.org/W2173248099","https://openalex.org/W2175915769","https://openalex.org/W2257238407","https://openalex.org/W2329310016","https://openalex.org/W2409330027","https://openalex.org/W2510202377","https://openalex.org/W2515385973","https://openalex.org/W2740489910","https://openalex.org/W2746553466","https://openalex.org/W2788079612","https://openalex.org/W2949117887","https://openalex.org/W2963146395","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4230129716"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517"],"abstract_inverted_index":{"We":[0,28,132,175],"study":[1],"the":[2,21,26,47,51,58,68,71,81,84,93,105,108,122,155,185],"problem":[3,61,94,123],"of":[4,33,50,73,95,99,107,121,173,184],"allocating":[5],"impressions":[6],"to":[7,19,42,111,127],"sellers":[8,52,156,161],"in":[9,88,125,170,182],"e-commerce":[10],"websites,":[11],"such":[12],"as":[13,62,144,146],"Amazon,":[14],"eBay":[15],"or":[16],"Taobao,":[17],"aiming":[18],"maximize":[20],"total":[22,186],"revenue":[23,79],"generated":[24,78],"by":[25,139],"platform.":[27],"employ":[29],"a":[30,63],"general":[31],"framework":[32],"reinforcement":[34,40],"mechanism":[35],"design,":[36],"which":[37,118,167],"uses":[38],"deep":[39],"learning":[41],"design":[43,112],"efficient":[44],"algorithms,":[45],"taking":[46],"strategic":[48],"behaviour":[49],"into":[53],"account.":[54],"Specifically,":[55],"we":[56,103,158],"model":[57],"impression":[59,86],"allocation":[60],"Markov":[64],"decision":[65],"process,":[66],"where":[67],"states":[69,100],"encode":[70],"history":[72],"impressions,":[74],"prices,":[75],"transactions":[76],"and":[77,80,97,101,130],"actions":[82],"are":[83],"possible":[85],"allocations":[87],"each":[89],"round.":[90],"To":[91],"tackle":[92],"continuity":[96],"high-dimensionality":[98],"actions,":[102],"adopt":[104],"ideas":[106],"DDPG":[109],"algorithm":[110,117],"an":[113],"actor-critic":[114],"policy":[115],"gradient":[116],"takes":[119],"advantage":[120],"domain":[124],"order":[126],"achieve":[128],"convergence":[129],"stability.":[131],"evaluate":[133],"our":[134],"proposed":[135],"algorithm,":[136],"coined":[137],"IA(GRU),":[138],"comparing":[140],"it":[141],"against":[142],"DDPG,":[143],"well":[145],"several":[147],"natural":[148],"heuristics,":[149],"under":[150],"different":[151],"rationality":[152],"models":[153],"for":[154],"-":[157],"assume":[159],"that":[160,177],"follow":[162],"well-known":[163],"no-regret":[164],"type":[165],"strategies":[166],"may":[168],"vary":[169],"their":[171],"degree":[172],"sophistication.":[174],"find":[176],"IA(GRU)":[178],"outperforms":[179],"all":[180],"algorithms":[181],"terms":[183],"revenue.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}