{"id":"https://openalex.org/W7167895533","doi":"https://doi.org/10.1145/3805712.3809577","title":"Large-Scale Online Learning for Generative List Recommendation in E-commerce: An Environment Policy Optimization Approach","display_name":"Large-Scale Online Learning for Generative List Recommendation in E-commerce: An Environment Policy Optimization Approach","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167895533","doi":"https://doi.org/10.1145/3805712.3809577"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809577","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809577","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101336430","display_name":"Yuan Wang","orcid":"https://orcid.org/0000-0002-3630-9179"},"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":"Yuan Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3630-9179","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390297","display_name":"Zhiyu Li","orcid":"https://orcid.org/0000-0002-8187-4177"},"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":"Zhiyu Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8187-4177","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140451490","display_name":"Ang Gao","orcid":"https://orcid.org/0009-0008-8964-801X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ang Gao","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8964-801X","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144692","display_name":"Changshuo Zhang","orcid":"https://orcid.org/0009-0001-8481-9421"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changshuo Zhang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8481-9421","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320847","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0001-7397-5632"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7397-5632","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7170-111X","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763939","display_name":"Quan Lin","orcid":"https://orcid.org/0009-0002-7149-5525"},"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":"Quan Lin","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-7149-5525","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94001585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1823","last_page":"1833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9230999946594238,"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":0.9230999946594238,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.009700000286102295,"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":0.009200000204145908,"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/recommender-system","display_name":"Recommender system","score":0.5485000014305115},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4837999939918518},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.43799999356269836},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.40220001339912415},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3790999948978424},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.37700000405311584},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.3714999854564667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070999979972839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6158000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839999914169312},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3790999948978424},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.37700000405311584},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809577","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809577","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809577","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1570963478","https://openalex.org/W2145339207","https://openalex.org/W2337233909","https://openalex.org/W2494566063","https://openalex.org/W2514091133","https://openalex.org/W2739826497","https://openalex.org/W2739916191","https://openalex.org/W2796727080","https://openalex.org/W2903088943","https://openalex.org/W2946327583","https://openalex.org/W2964247748","https://openalex.org/W2965893800","https://openalex.org/W2973171206","https://openalex.org/W3034950638","https://openalex.org/W3035590471","https://openalex.org/W3110889227","https://openalex.org/W3134652868","https://openalex.org/W3155690528","https://openalex.org/W3156002164","https://openalex.org/W3167758559","https://openalex.org/W3174606363","https://openalex.org/W3183218305","https://openalex.org/W4205841652","https://openalex.org/W4290927796","https://openalex.org/W4292022450","https://openalex.org/W4379914435","https://openalex.org/W4380136520","https://openalex.org/W4384625621","https://openalex.org/W4385261955","https://openalex.org/W4387846685","https://openalex.org/W4400525872","https://openalex.org/W4403220268","https://openalex.org/W4414034954","https://openalex.org/W4414359408","https://openalex.org/W7130573645","https://openalex.org/W7133224375"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"List":[1],"Recommendation":[2],"(GLR)":[3],"models":[4,32],"have":[5],"shown":[6],"superior":[7],"performance":[8,187,249],"in":[9,33,47,62,90,188,210,213,225,238],"E-commerce":[10,92],"by":[11,112],"directly":[12,138],"generating":[13],"high-quality":[14],"recommendation":[15,31,242],"lists":[16],"through":[17],"sequential":[18],"item":[19,175],"selection.":[20],"While":[21],"Online":[22],"Learning":[23],"(OL)":[24],"has":[25],"proven":[26],"valuable":[27],"for":[28,83,199,234],"streaming":[29,239],"point-wise":[30],"adapting":[34],"to":[35,41,50],"dynamic":[36,241],"user":[37,211],"preferences,":[38],"its":[39],"application":[40],"GLR":[42,64,105,200],"remains":[43],"largely":[44],"unexplored,":[45],"due":[46],"large":[48],"part":[49],"the":[51,84,114,117,120,126,147,194,220,227,247],"inefficiency":[52],"and":[53,76,163,169,230,240],"instability":[54],"of":[55,116,133,146,196,223,255],"conventional":[56],"on-policy":[57],"reinforcement":[58],"learning":[59,111,198],"algorithms":[60],"used":[61],"existing":[63],"approaches.":[65],"Existing":[66],"approaches":[67],"typically":[68],"rely":[69],"on":[70,167],"surrogate":[71],"losses,":[72],"which":[73,172],"provide":[74],"indirect":[75],"biased":[77],"gradient":[78,135,231],"estimates,":[79],"making":[80],"them":[81],"ill-suited":[82],"rapid,":[85],"subtle":[86],"distribution":[87],"shifts":[88],"common":[89],"real-world":[91],"environments.":[93,243],"In":[94],"this":[95],"paper,":[96],"we":[97],"propose":[98],"Environment":[99],"Policy":[100],"Optimization":[101],"(EPO),":[102],"a":[103,129,160,178,206,251],"novel":[104],"model":[106],"that":[107,125],"fundamentally":[108],"reshapes":[109],"policy":[110],"exploiting":[113],"differentiability":[115],"environment":[118],"within":[119],"Generator-Evaluator":[121],"framework.":[122],"EPO":[123,142,158,182,224,245],"recognizes":[124],"evaluator":[127],"is":[128],"neural":[130],"network,":[131],"capable":[132],"providing":[134,226],"signals.":[136],"By":[137],"utilizing":[139],"these":[140],"gradients,":[141],"enables":[143],"end-to-end":[144],"optimization":[145],"total":[148],"list-wise":[149],"reward\u2014the":[150],"true":[151],"objective.":[152],"To":[153],"ensure":[154],"differentiable":[155],"list":[156],"generation,":[157],"introduces":[159],"new":[161],"indexing":[162],"exploration":[164],"strategy":[165],"based":[166],"NeuralSort":[168],"Gumbel":[170],"noise,":[171],"relaxes":[173],"discrete":[174],"selection":[176],"into":[177],"continuous,":[179],"gradient-friendly":[180],"operation.":[181],"not":[183],"only":[184],"demonstrates":[185],"strong":[186],"offline":[189],"evaluations":[190],"but":[191],"also":[192],"unlocks":[193],"potential":[195],"online":[197,214],"at":[201],"an":[202],"industrial":[203],"scale,":[204],"yielding":[205],"1.18%":[207],"relative":[208],"improvement":[209],"clicks":[212],"A/B":[215],"tests.":[216],"The":[217],"results":[218],"underscore":[219],"critical":[221],"role":[222],"sensitivity,":[228],"stability,":[229],"fidelity":[232],"necessary":[233],"effective":[235],"real-time":[236],"adaptation":[237],"Moreover,":[244],"reached":[246],"baseline":[248],"with":[250],"training":[252],"time":[253],"deduction":[254],"76%":[256],"under":[257],"identical":[258],"hardware":[259],"conditions.":[260]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}