{"id":"https://openalex.org/W4396736348","doi":"https://doi.org/10.1145/3589334.3645534","title":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding","display_name":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396736348","doi":"https://doi.org/10.1145/3589334.3645534"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3645534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","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/A5019278984","display_name":"Haoming Li","orcid":"https://orcid.org/0009-0009-8221-0717"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoming Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102722801","display_name":"Yusen Huo","orcid":"https://orcid.org/0009-0006-8863-3209"},"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":"Yusen Huo","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086529405","display_name":"Shuai Dou","orcid":"https://orcid.org/0009-0000-0711-130X"},"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":"Shuai Dou","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087120799","display_name":"Zhenzhe Zheng","orcid":"https://orcid.org/0000-0002-5094-5331"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhe Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004272221","display_name":"Zhilin Zhang","orcid":"https://orcid.org/0000-0002-4251-8575"},"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":"Zhilin Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059373349","display_name":"Chuan Yu","orcid":"https://orcid.org/0000-0001-8094-1545"},"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":"Chuan Yu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739665","display_name":"Jian Xu","orcid":"https://orcid.org/0000-0003-3111-1005"},"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":"Jian Xu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059190563","display_name":"Fan Wu","orcid":"https://orcid.org/0000-0003-0965-9058"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5019278984"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.3627,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83142072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4193","last_page":"4203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/T12782","display_name":"Assembly Line Balancing Optimization","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/bidding","display_name":"Bidding","score":0.8663994073867798},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8441083431243896},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.749655544757843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7109903693199158},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.5088739395141602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49595484137535095},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4236636459827423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35126757621765137},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32579702138900757},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.150346040725708},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11341014504432678},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.09849220514297485},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08430629968643188},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.05997946858406067}],"concepts":[{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.8663994073867798},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8441083431243896},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.749655544757843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109903693199158},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.5088739395141602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49595484137535095},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4236636459827423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35126757621765137},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32579702138900757},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.150346040725708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11341014504432678},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.09849220514297485},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08430629968643188},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.05997946858406067},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3645534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8202041916","display_name":null,"funder_award_id":"Science and Technology Innovation 2030 ?``New Generation Artificial Intelligence' Major Project No. 2022ZD0119100","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2149822245","https://openalex.org/W2562337727","https://openalex.org/W2747329762","https://openalex.org/W2761873684","https://openalex.org/W2788376840","https://openalex.org/W2963523627","https://openalex.org/W3033324992","https://openalex.org/W3099947523","https://openalex.org/W3138939485","https://openalex.org/W3166393923","https://openalex.org/W4212774754","https://openalex.org/W4283796596","https://openalex.org/W4287259025"],"related_works":["https://openalex.org/W2355561715","https://openalex.org/W2355326491","https://openalex.org/W2389286292","https://openalex.org/W2360751371","https://openalex.org/W2387920521","https://openalex.org/W2389754756","https://openalex.org/W2382224273","https://openalex.org/W2373538886","https://openalex.org/W2360290312","https://openalex.org/W2369836678"],"abstract_inverted_index":{"In":[0,109],"online":[1,52,175],"advertising,":[2],"advertisers":[3],"participate":[4],"in":[5,42,51,64,96],"ad":[6,10],"auctions":[7],"to":[8,33,45,66,79,104,170],"acquire":[9],"opportunities,":[11],"often":[12],"by":[13,18,132,188],"utilizing":[14],"auto-bidding":[15,24,38,62],"tools":[16],"provided":[17],"demand-side":[19],"platforms":[20],"(DSPs).":[21],"The":[22,84],"current":[23],"algorithms":[25,74],"typically":[26],"employ":[27],"reinforcement":[28],"learning":[29],"(RL).":[30],"However,":[31],"due":[32],"safety":[34,173],"concerns,":[35],"most":[36],"RL-based":[37],"policies":[39],"are":[40],"trained":[41,85],"simulation,":[43],"leading":[44],"a":[46,68,81,153,166],"performance":[47,115],"degradation":[48],"when":[49],"deployed":[50,90],"environments.":[53],"To":[54,140],"narrow":[55],"this":[56,110,118,142],"gap,":[57],"we":[58,102,112,144,184],"can":[59,75,87],"deploy":[60],"multiple":[61],"agents":[63],"parallel":[65],"collect":[67],"large":[69],"interaction":[70],"dataset.":[71],"Offline":[72],"RL":[73,121,138,164],"then":[76],"be":[77,89],"utilized":[78],"train":[80],"new":[82],"policy.":[83],"policy":[86],"subsequently":[88],"for":[91,161,182],"further":[92],"data":[93,155,158],"collection,":[94],"resulting":[95],"an":[97],"iterative":[98,106,119,162],"training":[99],"framework,":[100,122],"which":[101,123,151],"refer":[103],"as":[105],"offline":[107,120,137,163,194],"RL.":[108],"work,":[111],"identify":[113],"the":[114,126,133,172,179,205],"bottleneck":[116],"of":[117,136,174,207],"originates":[124],"from":[125,165],"ineffective":[127],"exploration":[128,176],"and":[129,148,157,196],"exploitation":[130],"caused":[131],"inherent":[134],"conservatism":[135],"algorithms.":[139],"overcome":[141],"bottleneck,":[143],"propose":[145,185],"Trajectory-wise":[146],"Exploration":[147,187],"Exploitation":[149],"(TEE),":[150],"introduces":[152],"novel":[154],"collecting":[156],"utilization":[159],"method":[160],"trajectory":[167],"perspective.":[168],"Furthermore,":[169],"ensure":[171],"while":[177],"preserving":[178],"dataset":[180],"quality":[181],"TEE,":[183],"Safe":[186],"Adaptive":[189],"Action":[190],"Selection":[191],"(SEAS).":[192],"Both":[193],"experiments":[195,198],"real-world":[197],"on":[199],"Alibaba":[200],"display":[201],"advertising":[202],"platform":[203],"demonstrate":[204],"effectiveness":[206],"our":[208],"proposed":[209],"method.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}