{"id":"https://openalex.org/W3208231292","doi":"https://doi.org/10.1145/3459637.3482347","title":"Generative Inverse Deep Reinforcement Learning for Online Recommendation","display_name":"Generative Inverse Deep Reinforcement Learning for Online Recommendation","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3208231292","doi":"https://doi.org/10.1145/3459637.3482347","mag":"3208231292"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482347","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057487706","display_name":"Xiaocong Chen","orcid":"https://orcid.org/0000-0002-8849-4943"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaocong Chen","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618738","display_name":"Aixin Sun","orcid":"https://orcid.org/0000-0003-0764-4258"},"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":"Aixin Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076107706","display_name":"Xianzhi Wang","orcid":"https://orcid.org/0000-0001-9582-3445"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xianzhi Wang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006841485","display_name":"Xiwei Xu","orcid":"https://orcid.org/0000-0002-2273-1862"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiwei Xu","raw_affiliation_strings":["Data 61, CSIRO, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064683660","display_name":"Liming Zhu","orcid":"https://orcid.org/0000-0001-5839-3765"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liming Zhu","raw_affiliation_strings":["Data 61, CSIRO, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data 61, CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.784,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92662072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"201","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.995199978351593,"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":0.9828000068664551,"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":0.8677449226379395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891891002655029},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7121586799621582},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6359462738037109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6349015235900879},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.631999135017395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5619074702262878},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5472851991653442},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.521916389465332},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5112683773040771},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47523048520088196},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4256514012813568},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4203769564628601}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8677449226379395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891891002655029},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7121586799621582},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6359462738037109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6349015235900879},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.631999135017395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5619074702262878},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5472851991653442},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.521916389465332},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5112683773040771},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47523048520088196},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4256514012813568},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4203769564628601},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482347","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W91039700","https://openalex.org/W1512919909","https://openalex.org/W1999874108","https://openalex.org/W2099471712","https://openalex.org/W2101984404","https://openalex.org/W2156737235","https://openalex.org/W2290104316","https://openalex.org/W2434014514","https://openalex.org/W2785379783","https://openalex.org/W2787933113","https://openalex.org/W2809162153","https://openalex.org/W2914272066","https://openalex.org/W2949608212","https://openalex.org/W2951625652","https://openalex.org/W2963363446","https://openalex.org/W2963619374","https://openalex.org/W2963654596","https://openalex.org/W2964157711","https://openalex.org/W2984869362","https://openalex.org/W2996959725","https://openalex.org/W2997914278","https://openalex.org/W3029587262","https://openalex.org/W3035170973","https://openalex.org/W3098551837","https://openalex.org/W4232512588"],"related_works":["https://openalex.org/W2987280934","https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W3014948380","https://openalex.org/W1493875009","https://openalex.org/W2751624083"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,87],"learning":[2,29,67,88,111],"enables":[3],"an":[4,68,96,108,141],"agent":[5,65],"to":[6,21,26,51],"capture":[7],"users'":[8,120],"interest":[9,24,33],"through":[10],"dynamic":[11,73],"interactions":[12],"with":[13,157],"the":[14,28,53,59,64,79,92,104,125,147],"environment.":[15],"It":[16],"uses":[17],"a":[18,84,129,133],"reward":[19,39,98],"function":[20],"learn":[22],"user's":[23],"and":[25,56,122,145,149],"control":[27],"process,":[30],"attracting":[31],"great":[32],"in":[34,71],"recommendation":[35,60,75,105],"research.":[36],"However,":[37],"most":[38],"functions":[40],"are":[41,45],"manually":[42],"designed;":[43],"they":[44],"either":[46],"too":[47],"unrealistic":[48],"or":[49],"imprecise":[50],"reflect":[52],"variety,":[54],"dimensionality,":[55],"non-linearity":[57],"of":[58,94,151],"problem.":[61,112],"This":[62],"impedes":[63],"from":[66],"optimal":[69],"policy":[70,110,127],"highly":[72],"online":[74,142],"scenarios.":[76],"To":[77],"address":[78],"above":[80],"issue,":[81],"we":[82,102],"propose":[83],"generative":[85],"inverse":[86],"approach":[89,154],"that":[90],"avoids":[91],"need":[93],"defining":[95],"elaborative":[97],"function.":[99],"In":[100],"particular,":[101],"model":[103],"problem":[106],"as":[107],"automatic":[109],"We":[113,137],"first":[114],"generate":[115],"policies":[116],"based":[117,131],"on":[118,132,140],"observed":[119],"preferences":[121],"then":[123],"evaluate":[124],"learned":[126],"by":[128],"measurement":[130],"discriminative":[134],"actor-critic":[135],"network.":[136],"conduct":[138],"experiments":[139],"platform,":[143],"VirtualTB,":[144],"demonstrate":[146],"feasibility":[148],"effectiveness":[150],"our":[152],"proposed":[153],"via":[155],"comparisons":[156],"several":[158],"state-of-the-art":[159],"methods.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}