{"id":"https://openalex.org/W7118930706","doi":"https://doi.org/10.1145/3770854.3783950","title":"Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies","display_name":"Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7118930706","doi":"https://doi.org/10.1145/3770854.3783950"},"language":null,"primary_location":{"id":"doi:10.1145/3770854.3783950","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3783950","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3783950","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122090728","display_name":"Mingming Zhang","orcid":null},"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":"Mingming Zhang","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University Taobao & Tmall Group of Alibaba, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-1730-4584","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University Taobao & Tmall Group of Alibaba, Wuhan, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122213568","display_name":"Na Li","orcid":null},"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":"Na Li","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University Taobao & Tmall Group of Alibaba, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0000-3394-0056","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University Taobao & Tmall Group of Alibaba, Wuhan, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122027332","display_name":"Zhuang Feiqing","orcid":null},"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":"Feiqing Zhuang","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-3256-497X","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122186406","display_name":"Hongyang Zheng","orcid":null},"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":"Hongyang Zheng","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-7376-1991","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032006171","display_name":"Jiangbing Zhou","orcid":"https://orcid.org/0000-0002-1201-5360"},"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":"Jiangbing Zhou","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-7743-6644","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122199878","display_name":"Wang Wuyin","orcid":null},"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":"Wuyin Wang","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-4944-4817","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122259090","display_name":"Sheng-jie Sun","orcid":null},"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":"Shengjie Sun","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-1519-6682","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457822","display_name":"Xiaowei Chen","orcid":"https://orcid.org/0000-0001-6449-4247"},"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":"Xiaowei Chen","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-2175-1240","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108713708","display_name":"Junxiong Zhu","orcid":null},"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":"Junxiong Zhu","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-4350-5324","affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089307887","display_name":"Lixin Zou","orcid":"https://orcid.org/0000-0001-6755-871X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Zou","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6755-871X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122178468","display_name":"Chenliang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3144-6374","affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07355205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2573","last_page":"2583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.15809999406337738,"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":0.15809999406337738,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11320000141859055,"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":0.08889999985694885,"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":0.6001999974250793},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5594000220298767},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5523999929428101},{"id":"https://openalex.org/keywords/bidding","display_name":"Bidding","score":0.4523000121116638},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.42179998755455017},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4023999869823456},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6916000247001648},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5321000218391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49079999327659607},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3770854.3783950","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3783950","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.02754","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02754","pdf_url":"https://arxiv.org/pdf/2601.02754","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3770854.3783950","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3783950","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7473013270","display_name":null,"funder_award_id":"62272349","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7817342302","display_name":null,"funder_award_id":"U23A20305","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,51,84,100,109,113,117,124,128,140,161],"rapid":[2],"development":[3],"of":[4,53,93,116],"e-commerce,":[5],"auto-bidding":[6],"has":[7],"become":[8],"a":[9,39,63,76,133,202,209],"key":[10],"asset":[11],"in":[12,138,195,205,212],"optimizing":[13],"advertising":[14],"performance":[15],"under":[16],"diverse":[17],"advertiser":[18],"environments.":[19],"The":[20,46],"current":[21],"approaches":[22],"focus":[23],"on":[24,145,174],"reinforcement":[25],"learning":[26],"(RL)":[27],"and":[28,96,111,149,177,208],"generative":[29],"models.":[30],"These":[31],"efforts":[32],"imitate":[33],"offline":[34],"historical":[35],"behaviors":[36],"by":[37,160],"utilizing":[38],"complex":[40],"structure":[41],"with":[42,79],"expensive":[43],"hyperparameter":[44],"tuning.":[45],"suboptimal":[47,118],"trajectories":[48],"further":[49],"exacerbate":[50],"difficulty":[52],"policy":[54,94,103,125],"learning.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60,72,131],"proposes":[61],"QGA,":[62,71],"novel":[64],"Q-value":[65,77,134,163],"regularized":[66],"Generative":[67],"Auto-bidding":[68],"method.":[69],"In":[70],"propose":[73,132],"to":[74,104,121,191],"plug":[75],"regularization":[78],"double":[80],"Q-learning":[81],"strategy":[82],"into":[83],"Decision":[85],"Transformer":[86],"backbone.":[87],"This":[88,153],"design":[89],"enables":[90],"joint":[91],"optimization":[92],"imitation":[95],"action-value":[97],"maximization,":[98],"allowing":[99],"learned":[101],"bidding":[102],"both":[105],"leverage":[106],"experience":[107],"from":[108],"dataset":[110],"alleviate":[112],"adverse":[114],"impact":[115],"trajectories.":[119],"Furthermore,":[120],"safely":[122],"explore":[123],"space":[126],"beyond":[127],"data":[129],"distribution,":[130],"guided":[135,159],"dual-exploration":[136],"mechanism,":[137],"which":[139,165],"DT":[141],"model":[142],"is":[143,157],"conditioned":[144],"multiple":[146],"return-to-go":[147],"targets":[148],"locally":[150],"perturbed":[151],"actions.":[152],"entire":[154],"exploration":[155],"process":[156],"dynamically":[158],"aforementioned":[162],"module,":[164],"provides":[166],"principled":[167],"evaluation":[168],"for":[169],"each":[170],"candidate":[171],"action.":[172],"Experiments":[173],"public":[175],"benchmarks":[176],"simulation":[178],"environments":[179],"demonstrate":[180],"that":[181],"QGA":[182,200],"consistently":[183],"achieves":[184,201],"superior":[185],"or":[186],"highly":[187],"competitive":[188],"results":[189],"compared":[190],"existing":[192],"alternatives.":[193],"Notably,":[194],"large-scale":[196],"real-world":[197],"A/B":[198],"testing,":[199],"3.27%":[203],"increase":[204],"Ad":[206,213],"GMV":[207],"2.49%":[210],"improvement":[211],"ROI.":[214]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-01-08T00:00:00"}