{"id":"https://openalex.org/W3199755719","doi":"https://doi.org/10.1145/3460231.3474256","title":"Partially Observable Reinforcement Learning for Dialog-based Interactive Recommendation","display_name":"Partially Observable Reinforcement Learning for Dialog-based Interactive Recommendation","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3199755719","doi":"https://doi.org/10.1145/3460231.3474256","mag":"3199755719"},"language":"en","primary_location":{"id":"doi:10.1145/3460231.3474256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3474256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/55148.html>,","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102858602","display_name":"Yaxiong Wu","orcid":"https://orcid.org/0000-0002-1860-0122"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yaxiong Wu","raw_affiliation_strings":["University of Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["School of Computing cience University of Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing cience University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["University of Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102858602"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":2.56,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91274702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8562029600143433},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6862020492553711},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6815775632858276},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6676019430160522},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.575081467628479},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5628618001937866},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4936453104019165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4829930067062378},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.43088412284851074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4130197763442993},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3818652033805847},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3276563286781311},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2696376442909241},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2135315239429474},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.19558537006378174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8562029600143433},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6862020492553711},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6815775632858276},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6676019430160522},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.575081467628479},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5628618001937866},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4936453104019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4829930067062378},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.43088412284851074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4130197763442993},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3818652033805847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276563286781311},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2696376442909241},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2135315239429474},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.19558537006378174},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3460231.3474256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460231.3474256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fifteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:246701","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/55148.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:246701","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/55148.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1989121949","display_name":null,"funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5187265158","display_name":"Closed-Loop Data Science for Complex, Computationally- and Data-Intensive Analytics","funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8352026019","display_name":null,"funder_award_id":"R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1522301498","https://openalex.org/W1528802670","https://openalex.org/W1924770834","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2138108551","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2194775991","https://openalex.org/W2471768434","https://openalex.org/W2557283755","https://openalex.org/W2783272285","https://openalex.org/W2787933113","https://openalex.org/W2798503981","https://openalex.org/W2798734012","https://openalex.org/W2803743229","https://openalex.org/W2898076813","https://openalex.org/W2902572901","https://openalex.org/W2949395487","https://openalex.org/W2950133940","https://openalex.org/W2952032963","https://openalex.org/W2962938178","https://openalex.org/W2963084599","https://openalex.org/W2963367478","https://openalex.org/W2963842088","https://openalex.org/W2964112275","https://openalex.org/W2964316331","https://openalex.org/W2981211936","https://openalex.org/W2996960746","https://openalex.org/W2997662139","https://openalex.org/W3034853385","https://openalex.org/W3040127368","https://openalex.org/W3116062118","https://openalex.org/W3116249021","https://openalex.org/W3123936891","https://openalex.org/W3165654682"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W4246582778","https://openalex.org/W2171219280","https://openalex.org/W2174703168","https://openalex.org/W3123911006","https://openalex.org/W2512370135","https://openalex.org/W4236658683","https://openalex.org/W2020463334","https://openalex.org/W2026182709"],"abstract_inverted_index":{"A":[0],"dialog-based":[1,139],"interactive":[2],"recommendation":[3,31,78,140,241],"task":[4],"is":[5,216],"where":[6],"users":[7],"can":[8,35,74,109],"express":[9],"natural-language":[10,27,60],"feedback":[11,61],"when":[12,90],"interacting":[13],"with":[14,146,176],"the":[15,19,24,30,38,47,55,68,86,99,111,142,153,173,177,182,190,193,197,220,223,228,266],"recommender":[16,39,126],"system.":[17],"However,":[18],"users\u2019":[20,48,56,69,87,154,167,198,225],"feedback,":[21],"which":[22,73,214],"takes":[23],"form":[25,100],"of":[26,46,54,85,93,101,192,246],"critiques":[28],"about":[29],"at":[32],"each":[33],"iteration,":[34],"only":[36],"allow":[37],"system":[40],"to":[41,65,150,163,171,180,188,218,265],"obtain":[42],"a":[43,81,102,114,119,125,131,137,169,211],"partial":[44,52,132],"portrayal":[45],"preferences.":[49],"Indeed,":[50],"such":[51,130],"observations":[53],"preferences":[57,70,155,175,195,226],"from":[58],"their":[59],"make":[62],"it":[63],"challenging":[64],"correctly":[66],"track":[67,164],"over":[71,156],"time,":[72],"result":[75],"in":[76,91,98,231,263],"poor":[77],"performances":[79],"and":[80,121,165,185,227,235,251],"less":[82],"effective":[83],"satisfaction":[84],"information":[88],"needs":[89],"presence":[92],"limited":[94],"iterations.":[95],"Reinforcement":[96],"learning,":[97],"partially":[103,115],"observable":[104,116],"Markov":[105],"decision":[106],"process":[107],"(POMDP),":[108],"simulate":[110],"interactions":[112],"between":[113,222],"environment":[117],"(i.e.":[118,124],"user)":[120],"an":[122,161,186],"agent":[123],"system).":[127],"To":[128],"alleviate":[129],"observation":[133],"issue,":[134],"we":[135,159,204],"propose":[136],"novel":[138],"model,":[141,145],"Estimator-Generator-Evaluator":[143],"(EGE)":[144],"Q-learning":[147],"for":[148],"POMDP,":[149],"effectively":[151],"incorporate":[152],"time.":[157],"Specifically,":[158],"leverage":[160],"Estimator":[162],"estimate":[166],"preferences,":[168],"Generator":[170],"match":[172],"estimated":[174,194],"candidate":[178],"items":[179,230],"rank":[181],"next":[183],"recommendations,":[184],"Evaluator":[187],"judge":[189],"quality":[191],"considering":[196],"historical":[199],"feedback.":[200],"Following":[201],"previous":[202],"work,":[203],"train":[205],"our":[206,256],"EGE":[207,258],"model":[208,259],"by":[209],"using":[210],"user":[212],"simulator":[213],"itself":[215],"trained":[217],"describe":[219],"differences":[221],"target":[224],"recommended":[229],"natural":[232],"language.":[233],"Thorough":[234],"extensive":[236],"experiments":[237],"conducted":[238],"on":[239],"two":[240],"datasets":[242],"\u2013":[243,253],"addressing":[244],"images":[245],"fashion":[247],"products":[248],"(namely":[249],"dresses":[250],"shoes)":[252],"demonstrate":[254],"that":[255],"proposed":[257],"yields":[260],"significant":[261],"improvements":[262],"comparison":[264],"existing":[267],"state-of-the-art":[268],"baseline":[269],"models.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}