{"id":"https://openalex.org/W7204822602","doi":"https://doi.org/10.48550/arxiv.2608.28065","title":"Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning","display_name":"Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204822602","doi":"https://doi.org/10.48550/arxiv.2608.28065"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28065","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28065","pdf_url":"https://arxiv.org/pdf/2608.28065","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,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048936923","display_name":"Zilin Zhao","orcid":"https://orcid.org/0000-0002-7002-9306","observed_orcids":["https://orcid.org/0000-0002-7002-9306","https://orcid.org/0009-0003-2190-958X","https://orcid.org/0009-0006-7925-2359"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Zilin","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology , Nanjing University Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology , Nanjing University Nanjing , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148799712","display_name":"Han Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Han","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology , Nanjing University Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology , Nanjing University Nanjing , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148762058","display_name":"Tianpei Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Tianpei","raw_affiliation_strings":["ByteDance Beijing , China","State Key Laboratory of Novel Software Technology , Nanjing University Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Beijing , China","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology , Nanjing University Nanjing , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061824230","display_name":"Fangsheng Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Fangsheng","raw_affiliation_strings":["ByteDance Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148770653","display_name":"Yanfei Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Yanfei","raw_affiliation_strings":["ByteDance Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148793508","display_name":"Kan Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Kan","raw_affiliation_strings":["ByteDance Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148759310","display_name":"Yi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yi","raw_affiliation_strings":["ByteDance Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111270998","display_name":"Yiming Zong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zong, Yiming","raw_affiliation_strings":["The Hong Kong University of Science and Technology Hong Kong , China ByteDance Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology Hong Kong , China ByteDance Beijing , China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148809724","display_name":"Hao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":["Xue ByteDance Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xue ByteDance Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100587147","display_name":"Yinsong Xue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Yinsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.490200012922287,"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":0.490200012922287,"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":0.37059998512268066,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.05009999871253967,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/incentive-allocation","display_name":"incentive allocation","score":0.9860000014305115},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.5120000243186951},{"id":"https://openalex.org/keywords/user-engagement","display_name":"user engagement","score":0.5339999794960022},{"id":"https://openalex.org/keywords/net-profit-maximization","display_name":"net profit maximization","score":0.4869999885559082},{"id":"https://openalex.org/keywords/auto-bidding","display_name":"auto-bidding","score":0.4830000102519989},{"id":"https://openalex.org/keywords/target-marketing","display_name":"targeted marketing","score":0.8840000033378601}],"concepts":[{"id":"https://openalex.org/C2780602052","wikidata":"https://www.wikidata.org/wiki/Q289845","display_name":"Monetization","level":2,"score":0.8198000192642212},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.7853000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6897000074386597},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C3859990","wikidata":"https://www.wikidata.org/wiki/Q382996","display_name":"Incentive program","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2754000127315521},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26159998774528503}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28065","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28065","pdf_url":"https://arxiv.org/pdf/2608.28065","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,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28065","doi":"https://doi.org/10.48550/arxiv.2608.28065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28065","pdf_url":null,"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,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28065","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28065","pdf_url":"https://arxiv.org/pdf/2608.28065","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,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204822602.pdf","grobid_xml":"https://content.openalex.org/works/W7204822602.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4281756788","https://openalex.org/W7201915046","https://openalex.org/W3210703899","https://openalex.org/W2988150581","https://openalex.org/W4412876956","https://openalex.org/W4286235880","https://openalex.org/W4306317257","https://openalex.org/W2890699433","https://openalex.org/W4313242248","https://openalex.org/W3157410348"],"abstract_inverted_index":{"Complete":[0],"your":[1],"ad":[2,21,93,102,133],"view":[3],"and":[4,27,62,77,112,132,163,185],"grab":[5],"a":[6,12,16,68,126,172],"5-cent":[7],"bonus!":[8],"In":[9],"incentivized":[10],"advertising,":[11],"platform":[13],"promises":[14],"users":[15],"bonus":[17],"before":[18],"observing":[19],"downstream":[20],"revenue,":[22,74,134],"encouraging":[23],"them":[24],"to":[25,182,203],"click":[26],"complete":[28],"ads.":[29],"It":[30,124],"must":[31],"balance":[32],"the":[33,39,101,107,169,190],"incentive":[34,65,122],"promised":[35],"in":[36],"advance":[37],"against":[38],"revenue":[40],"realized":[41],"afterward:":[42],"insufficient":[43],"incentives":[44,50,56,99],"forfeit":[45],"monetization":[46,103],"opportunities,":[47,94],"whereas":[48,201],"excessive":[49],"reduce":[51],"net":[52,195],"profit.":[53],"Because":[54],"current":[55],"may":[57],"also":[58],"shape":[59],"user":[60,130],"expectations":[61],"future":[63],"engagement,":[64],"allocation":[66],"is":[67],"sequential":[69,121],"decision":[70],"problem":[71,108],"with":[72],"delayed":[73],"cost":[75],"sensitivity,":[76],"carryover":[78],"effects.":[79],"Existing":[80],"work":[81],"has":[82],"not":[83],"studied":[84],"decision-making":[85],"algorithms":[86],"for":[87,119],"this":[88],"setting.":[89],"Auto-bidding":[90],"assumes":[91],"available":[92],"while":[95],"targeted":[96],"promotion":[97],"optimizes":[98],"outside":[100],"pipeline.":[104],"We":[105],"formulate":[106],"as":[109],"an":[110,114],"MDP":[111],"develop":[113],"offline":[115,174,183],"model-based":[116],"RL":[117,184],"framework":[118],"cost-controllable":[120],"allocation.":[123],"learns":[125],"world":[127],"model":[128],"of":[129],"feedback":[131],"then":[135,186],"performs":[136],"conservative":[137],"policy":[138,147],"optimization.":[139],"An":[140],"independent":[141],"counterfactual":[142],"scorer":[143,170],"evaluates":[144],"each":[145],"learned":[146],"on":[148,159],"held-out":[149],"logs,":[150],"enabling":[151],"pre-launch":[152],"selection":[153],"without":[154],"costly":[155],"online":[156,164],"exposure.":[157],"Experiments":[158],"large-scale":[160],"industrial":[161],"data":[162],"A/B":[165],"tests":[166],"show":[167],"that":[168],"provides":[171],"stable":[173],"signal.":[175],"The":[176],"deployment":[177],"path":[178],"from":[179],"causal":[180],"inference":[181],"Offline-MBRL":[187],"further":[188],"validates":[189],"framework:":[191],"MB-IQL":[192],"improves":[193],"per-user":[194],"profit":[196],"by":[197,208],"7.96\\%":[198],"over":[199],"TD3+BC,":[200],"reverting":[202],"plain":[204],"IQL":[205],"reduces":[206],"it":[207],"6.56\\%":[209],"(both":[210],"\\(p<0.0001\\)).":[211]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-01T00:00:00"}