[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117462-en":3,"doc-seo-117462-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117462,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Reinforcing Automated Machine Learning - Bridging AutoML and Reinforcement Learning","This thesis studies how reinforcement learning can be used to strengthen automated machine learning, focusing on dynamic algorithm configuration during runtime. It addresses the adoption gap caused by the tightly coupled data collection and training loop in reinforcement learning, where data distributions and optimal strategies shift as the agent improves. The work extends algorithm configuration with dynamic analysis, maps key design decisions in reinforcement learning, and introduces contextual reinforcement learning to improve generalizability. It delivers actionable guidance for practitioners and a foundation for future automated reinforcement learning research.","Reinforcing Automated Machine Learning  \nBridging AutoML and Reinforcement Learning  \nVon der Fakultät für Elektrotechnik und Informatik der Gottfried Wilhelm Leibniz Universität Hannover zur Erlangung des Grades Doktorin der Naturwissenschaften (Dr. rer. nat.) genehmigte Dissertation von:  \nVon Frau M.Sc.  \nTheresa Eimer  \n2024  \nReferent: Prof. Dr. Marius Lindauer (Leibniz Universität Hannover)  \nKorreferenten: Jun.-Prof. Dr. Alexander Dockhorn (Leibniz Universität Hannover), Prof. Dr. Joschka Bödecker (Albert-Ludwigs Universität Freiburg)  \nTag der Promotion: 18.11.2024  \nAbstract  \nReinforcement Learning-Automated Machine Learning -Hyperparameter Optimization  \nReinforcement learning is a machine learning paradigm that allows learning through interaction. It intertwines data collection and model training into a single problem statement, enabling the solution of complex sequential decision making problems in domains like robotics, biology or physics. Not included in this list is the domain of automated machine learning, which aims to automatically configure machine learning algorithms for optimal performance on a given task - even though we have long known that sequential decision making is important in many facets of automated machine learning. This lack of adoption of reinforcement learning is potentially due to the fact that the entanglement of data collection and learning in reinforcement learning makes for a challenging machine learning setting; since the distribution of data seen during training shifts substantially as the agent improves, the optimal solution strategy-including the choice of algorithm, algorithm components, hyperparameters and even task variation-can shift as well. Thus applying reinforcement learning directly to an automated machine learning task might not be possible without considerable effort and expertise. This thesis bridges the gap between the fields by motivating the use of reinforcement learning in automated machine learning for dynamic algorithm configuration, a novel paradigm for configuring algorithms during their runtime. In turn, applying reinforcement learning in automated machine learning leads us to a closer examination of how to configure reinforcement learning itself to be efficient, reliable and generalizable when applied to new domains. We accomplish this in three parts: i. extending the algorithm configuration paradigm to allow the dynamic configuration and analysis of algorithms;  \nii. a principled investigation of the landscape of design decisions in reinforcement learning and; iii. laying the groundwork for generalization of reinforcement learning configuration approaches through contextual reinforcement learning. An important focus throughout is providing insights into the inner workings of reinforcement learning with respect to its design decisions, as of yet underexplored territory. Thus we are able to provide actionable recommendations for reinforcement learning practitioners as well as a broad base for future work on automated reinforcement learning. Overall, this thesis provides an in-depth look into the intersection of automated machine learning and reinforcement learning. We believe it will serve asa foundation for a closer connection between the fields by demonstrating the great potential of reinforcement learning for automated machine learning and vice versa.  \niii  \nZusammenfassung  \nBestärkendes Lernen-Automatisiertes Maschinelles Lernen -Hyperparameter Optimierung  \nBestärkendes Lernen ist ein Paradigma des maschinelles Lernens, das Lernen durch Interaktion ermöglicht. Es verknüpft die Datenerfassung und das Modelltraining zu einem Ablauf, wodurch die Lösung komplexer sequentieller Entscheidungsproblemein Bereichen wie Robotik, Biologie oder Physik ermöglicht wird. Nicht in dieser Liste enthalten ist der Bereich des automatisierten maschinellen Lernens, der daraufabzielt, maschinelle Lernalgorithmen automatisch für eine optimale Leistung zukonfigurieren – obwohl w","cbCaigtrrhdSYMAt","https://ap.wps.com/l/cbCaigtrrhdSYMAt","pdf",1533067,1,104,"English","en",105,"# Abstract\n## Reinforcement learning - Automated machine learning - Hyperparameter optimization\n## Bridging reinforcement learning and AutoML through dynamic configuration\n## Three-part approach: dynamic algorithm configuration, design decision landscape, and contextual generalization","[{\"question\":\"Why is reinforcement learning difficult to apply directly to automated machine learning tasks?\",\"answer\":\"Because reinforcement learning entangles data collection with training, the data distribution changes substantially as the agent improves, which can shift the optimal strategy, including algorithms, hyperparameters, and task variation.\"},{\"question\":\"What core contribution does the thesis make to connect AutoML and reinforcement learning?\",\"answer\":\"It motivates using reinforcement learning in automated machine learning for dynamic algorithm configuration, enabling algorithms to be configured during their runtime.\"},{\"question\":\"What are the three main parts of the proposed approach?\",\"answer\":\"First, extend algorithm configuration for dynamic configuration and analysis; second, investigate the landscape of design decisions in reinforcement learning; third, build groundwork for generalization via contextual reinforcement learning.\"}]","Reinforcing Automated Machine Learning - Bridging AutoML and Reinforcement Learning | PDF",1785675970,262,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"reinforcing-automated-machine-learning-bridging-automl-and-reinforcement-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/reinforcing-automated-machine-learning-bridging-automl-and-reinforcement-learning/117462/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is reinforcement learning difficult to apply directly to automated machine learning tasks?","Question",{"text":75,"@type":76},"Because reinforcement learning entangles data collection with training, the data distribution changes substantially as the agent improves, which can shift the optimal strategy, including algorithms, hyperparameters, and task variation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What core contribution does the thesis make to connect AutoML and reinforcement learning?",{"text":80,"@type":76},"It motivates using reinforcement learning in automated machine learning for dynamic algorithm configuration, enabling algorithms to be configured during their runtime.",{"name":82,"@type":73,"acceptedAnswer":83},"What are the three main parts of the proposed approach?",{"text":84,"@type":76},"First, extend algorithm configuration for dynamic configuration and analysis; second, investigate the landscape of design decisions in reinforcement learning; third, build groundwork for generalization via contextual reinforcement learning.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]