{"id":"https://openalex.org/W2951625652","doi":"https://doi.org/10.1145/3292500.3330933","title":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","display_name":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2951625652","doi":"https://doi.org/10.1145/3292500.3330933","mag":"2951625652"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5002985691","display_name":"Wenjie Shang","orcid":"https://orcid.org/0000-0002-9331-4062"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjie Shang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008990445","display_name":"Qingyang Li","orcid":"https://orcid.org/0000-0003-2602-9250"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Li","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085579946","display_name":"Zhiwei Qin","orcid":"https://orcid.org/0000-0001-5383-4816"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Qin","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112633752","display_name":"Yiping Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiping Meng","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002985691"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":4.2005,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95315764,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"566","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9958000183105469,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7889653444290161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7578976154327393},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6272094249725342},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6052334308624268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.573436975479126},{"id":"https://openalex.org/keywords/learning-environment","display_name":"Learning environment","score":0.4209126830101013}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7889653444290161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578976154327393},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6272094249725342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6052334308624268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573436975479126},{"id":"https://openalex.org/C2778365744","wikidata":"https://www.wikidata.org/wiki/Q2426689","display_name":"Learning environment","level":2,"score":0.4209126830101013},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1771410628","https://openalex.org/W1986014385","https://openalex.org/W2031571562","https://openalex.org/W2051228319","https://openalex.org/W2143117649","https://openalex.org/W2145339207","https://openalex.org/W2184746314","https://openalex.org/W2434014514","https://openalex.org/W2566467060","https://openalex.org/W2620393362","https://openalex.org/W2740242110","https://openalex.org/W2802494201","https://openalex.org/W2804132768","https://openalex.org/W2808805866","https://openalex.org/W2907354314","https://openalex.org/W2950946978","https://openalex.org/W2962957031","https://openalex.org/W4247950230"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,75,170],"aims":[2],"at":[3],"searching":[4],"the":[5,23,39,43,53,56,61,71,82,88,93,118,129,136,156,160,176,182,187,211,218,227,241,248,263,267],"best":[6],"policy":[7,24,40,256],"model":[8,91],"for":[9,17,185],"decision":[10],"making,":[11],"and":[12,180,216,244],"has":[13],"been":[14],"shown":[15],"powerful":[16],"sequential":[18],"recommendations.":[19],"The":[20,79,120],"training":[21,41,186],"of":[22,73,81,128,196,220,230,266],"by":[25,134],"reinforcement":[26,74],"learning,":[27],"however,":[28,38],"is":[29,64],"placed":[30],"in":[31,42,55,76,152,193,226,262],"an":[32,48,66,125,194,203],"environment.":[33,57,130],"In":[34,131],"many":[35],"real-world":[36,96],"applications,":[37],"real":[44,212,228,268],"environment":[45,83,106,148,157,249],"can":[46,123,238,246],"cause":[47],"unbearable":[49],"cost,":[50],"due":[51],"to":[52,69,86,102,154,174,214],"exploration":[54],"Environment":[58],"reconstruction":[59,80,127,149],"from":[60,92,210],"past":[62],"data":[63],"thus":[65,245],"appealing":[67],"way":[68],"release":[70],"power":[72],"these":[77],"applications.":[78],"is,":[84],"basically,":[85],"extract":[87],"casual":[89],"effect":[90],"data.":[94,119],"However,":[95],"applications":[97],"are":[98,112],"often":[99],"too":[100],"complex":[101],"offer":[103],"fully":[104],"observable":[105],"information.":[107],"Therefore,":[108],"quite":[109],"possibly":[110],"there":[111],"unobserved":[113],"confounding":[114],"variables":[115],"lying":[116],"behind":[117],"hidden":[121,137,141,161,242],"confounder":[122,138,177],"obstruct":[124],"effective":[126],"this":[132],"paper,":[133],"treating":[135],"as":[139],"a":[140,145,165,254,258],"policy,":[142,179],"we":[143],"propose":[144],"deconfounded":[146],"multi-agent":[147,166],"(DEMER)":[150],"approach":[151],"order":[153],"learn":[155],"together":[158],"with":[159,257],"confounder.":[162],"DEMER":[163,192,225,237,251],"adopts":[164],"generative":[167],"adversarial":[168],"imitation":[169],"framework.":[171],"It":[172],"proposes":[173],"introduce":[175],"embedded":[178],"use":[181,202],"compatible":[183],"discriminator":[184],"policies.":[188],"We":[189,200,222],"then":[190,223],"apply":[191],"application":[195,229],"driver":[197,205],"program":[198,206],"recommendation.":[199],"firstly":[201],"artificial":[204],"recommendation":[207,255],"environment,":[208],"abstracted":[209],"application,":[213],"verify":[215],"analyze":[217],"effectiveness":[219],"DEMER.":[221],"test":[224,264],"Didi":[231],"Chuxing.":[232],"Experiment":[233],"results":[234],"show":[235],"that":[236],"effectively":[239],"reconstruct":[240],"confounder,":[243],"build":[247],"better.":[250],"also":[252],"derives":[253],"significantly":[259],"improved":[260],"performance":[261],"phase":[265],"application.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}