[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-248191-105":53,"doc-detail-248191-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","an-adaptable-budget-planner-for-enhancing-budget-constrained-auto-bidding-in-online-advertising","An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising","","In online advertising, advertisers use autobidding to compete for impression opportunities under strict budget limits, aiming to maximize cumulative value from winning impressions. The task is difficult because bidding environments differ across advertisers and incoming impression information is highly random. ABPlanner is introduced as a few-shot adaptable budget planner built on a hierarchical bidding framework. It allocates budgets across short stages and adapts episode by episode via in-context reinforcement learning, enabling rapid personalization with limited data. Simulation and real-world A/B tests verify improved cumulative value for auto-bidders.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":51,"@type":70,"position":76},"https://docshare.wps.com/template/general/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/an-adaptable-budget-planner-for-enhancing-budget-constrained-auto-bidding-in-online-advertising/248191/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/an-adaptable-budget-planner-for-enhancing-budget-constrained-auto-bidding-in-online-advertising/248191.png","ImageObject",442,249,{"name":88,"@type":89},"Violet","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-09-22","2026-09-12",true,{"@type":98,"interactionType":99,"userInteractionCount":76},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What problem does ABPlanner address in online advertising?","Question",{"text":108,"@type":109},"ABPlanner targets budget-constrained auto-bidding, where the goal is to maximize cumulative value of winning impressions while respecting a limited budget.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"How does ABPlanner improve adaptability across different advertisers?",{"text":113,"@type":109},"It adjusts a budget allocation plan episode by episode using data from previous episodes as prompts, enabling few-shot adaptation to new advertisers.",{"name":115,"@type":106,"acceptedAnswer":116},"What framework does ABPlanner use to manage the bidding process?",{"text":117,"@type":109},"ABPlanner relies on a hierarchical bidding framework that decomposes a long bidding episode into short stages, with a high-level planner allocating budgets and a low-level autobidder bidding within each stage.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},248191,1789244771,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":50,"category_name":51,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":76,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":20,"language":135,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":61,"update_tm":125,"read_time":47},4398048950312,"https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908","arXiv :2502 .05187v1 [ cs .GT] 26 Jan 2025  \nAn Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising  \nZhijian Duan 1 ,2 ,∗ , Yusen Huo3 , Tianyu Wang3 , Zhilin Zhang3 , Yeshu Li3 , Chuan Yu3 , Jian Xu3 , Bo Zheng3 , Xiaotie Deng 1 ,2  \n1 School of Computer Science, Peking University, Beijing, China  \n2 Center on Frontiers of Computing Studies, Peking University, Beijing, China  \n3 Alibaba Group, Beijing, China  \n[zjduan@pku. edu. cn](zjduan@pku. edu. cn),  \n{huoyusen. huoyusen, yves. wty, [zhangzhilin. pt](zhangzhilin. pt}@alibaba-inc. com)[}](zhangzhilin. pt}@alibaba-inc. com)[@alibaba-inc. com](zhangzhilin. pt}@alibaba-inc. com),{liyeshu. lys, yuchuan. yc, xiyu. xj, [bozheng](bozheng}@alibaba-inc. com)[}](bozheng}@alibaba-inc. com)[@alibaba-inc. com](bozheng}@alibaba-inc. com),  \n[xiaotie@pku. edu. cn](xiaotie@pku. edu. cn)  \nAbstract  \nIn online advertising, advertisers commonly utilize autobidding services to bid for impression opportunities. Atypical objective of the auto-bidder is to optimize the advertiser’s cumulative value of winning impressions within specified budget constraints. However, such a problem is challenging due to the complex bidding environment faced by diverse advertisers. To address this challenge, we introduce ABPlanner, a few-shot adaptable budget planner designed to improve budget-constrained autobidding. ABPlanner is based on a hierarchical bidding framework that decomposes the bidding process into shorter, manageable stages. Within this framework, ABPlanner allocates the budget across all stages, allowing a low-level auto-bidder to bids based on the budget allocation plan. The adaptability of ABPlanner is achieved through a sequential decision-making approach, inspired by in-context reinforcement learning. For each advertiser, ABPlanner adjusts the budget allocation plan episode by episode, using data from previous episodes as prompt for current decisions. This enables ABPlanner to quickly adapt to different advertisers with few-shot data, providing a sample-efficient solution. Extensive simulation experiments and real-world A/B testing validate the effectiveness of ABPlanner, demonstrating its capability to enhance the cumulative value achieved by auto-bidders.  \n*This work is done during internship at Alibaba Group.  \n1 Introduction  \nReal-Time Bidding (RTB) plays a crucial role in online advertising, where an ad auction is triggered in realtime whenever an ad impression opportunity arises [Ou et al. , 2023a] . The speed and efficiency of RTB enable advertisers to target specific audiences and optimize their campaigns in real time. To navigate the complex and dynamic nature of the advertising landscape, advertisers often turn to auto-bidding strategies [Aggarwal et al. , 2019] . Auto-bidding systems leverage algorithms and machine learning models to make rapid and informed bidding decisions on behalf of advertisers.  \nOne primary objective of auto-bidders is to maximize the cumulative value of winning impressions for advertisers while adhering to specified budget constraints [Balseiro and Gur, 2019 , Chen et al. , 2023b] . Since the values and prices of arriving impressions are initially unknown, such a budget-constrained bidding can be viewed as an online stochastic knapsack problem [Hao et al. , 2020] . In this context, auto-bidders ideally aim to win impressions with high values and low market prices, that is, impressions with high cost-performance ratios, to effectively achieve their objectives [Zhou et al. , 2008 , Linet al. , 2016 , Maehara et al. , 2018] . However, this task is challenging due to the significant randomness in the fine-grained information of each incoming impression, and the bidding process within an episode involves numerous impressions. Additionally, different advertisers faces different bidding environments, which complicates  \nthe optimization of bidding strategies for each individual advertiser [Zhang et al. , 2023] .  \nTo addr","cbCaipGtEj4ZM8cM","https://ap.wps.com/l/cbCaipGtEj4ZM8cM","pdf",863951,"English","# Introduction\n## Real-Time Bidding and Auto-Bidding\n## Budget-Constrained Objective and Challenges\n## Proposed Approach: ABPlanner\n## Hierarchical Framework and Sequential Adaptation","[{\"question\":\"What problem does ABPlanner address in online advertising?\",\"answer\":\"ABPlanner targets budget-constrained auto-bidding, where the goal is to maximize cumulative value of winning impressions while respecting a limited budget.\"},{\"question\":\"How does ABPlanner improve adaptability across different advertisers?\",\"answer\":\"It adjusts a budget allocation plan episode by episode using data from previous episodes as prompts, enabling few-shot adaptation to new advertisers.\"},{\"question\":\"What framework does ABPlanner use to manage the bidding process?\",\"answer\":\"ABPlanner relies on a hierarchical bidding framework that decomposes a long bidding episode into short stages, with a high-level planner allocating budgets and a low-level autobidder bidding within each stage.\"}]","An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising | PDF"]