{"id":39000,"date":"2025-03-10T12:10:35","date_gmt":"2025-03-10T11:10:35","guid":{"rendered":"https:\/\/www.l3s.de\/?page_id=39000"},"modified":"2025-09-18T14:08:25","modified_gmt":"2025-09-18T12:08:25","slug":"rogerl","status":"publish","type":"page","link":"https:\/\/www.l3s.de\/de\/research-at-l3s\/all-projects\/rogerl\/","title":{"rendered":"RoGeRL"},"content":{"rendered":"
\n \n
\n \n \n
\n \n
\n \n
\n \n
\n
\n \n \n
\n \n
\n \n
\n
\n \n \n \"\"\n
<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n \n <\/div>\n
\n \n
\n \n
\n
\n \n \n
\n \n
\n \n \n
\n

Start:<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n

\n
\n \n \n
\n \n
\n \n \n
\n

01.01.2025<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n

\n \n
\n \n
\n
\n \n \n
\n \n
\n \n \n
\n

Ende:<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n

\n
\n \n \n
\n \n
\n \n \n
\n

31.12.2028<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n

\n \n
\n \n
\n
\n \n \n
\n \n
\n \n \n
\n

Webseite:<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n

\n
\n \n \n
\n \n
\n \n
–<\/span><\/a>\n <\/span>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n
\n \n \n
\n \n
\n \n <\/div>\n
\n \n
\n \n
\n
\n \n \n
\n \n
\n \n
\n \n \n

RoGeRL<\/h2>\n <\/div>\n <\/div>\n
\n \n \n
\n

Robust and General Reinforcement Learning via AutoML<\/p>\n <\/div>\n <\/div>\n

\n \n <\/div>\n
\n \n \n
\n

Reinforcement Learning (RL) erm\u00f6glicht Lernen durch Interaktion mit der Umgebung. Daher ist es ein Bestandteil von KI-Systemen f\u00fcr sequenzielle Entscheidungen, z. B. in der Robotik, in Naturwissenschaften wie Physik oder Medizin oder bei gro\u00dfen Sprachmodellen. <\/p>\n

RL ist jedoch nicht nur leistungsf\u00e4hig, sondern auch schwer anwendbar: Aktuelle Methoden sind tendenziell instabil, besitzen nur begrenzte Verallgemeinerungsf\u00e4higkeiten und ihr Erfolg h\u00e4ngt stark von ihren Designentscheidungen ab. In den letzten Jahren haben Methoden des automatisierten RL (AutoRL) an Zugkraft gewonnen, um durch systematische und datengesteuerte Ans\u00e4tze eine bessere Leistung, Robustheit und Trainingseffizienz zu erreichen. Unser Ziel ist es, sowohl die Effizienz als auch die Robustheit von AutoRL zu verbessern, um eine breite Nutzung dieser Werkzeuge f\u00fcr RL-Anwender und Forscher gleicherma\u00dfen zu erm\u00f6glichen. AutoRL wird dazu beitragen, das RL-Training zu demokratisieren und damit neue M\u00f6glichkeiten in allen Bereichen der RL-Forschung und -Anwendungen zu er\u00f6ffnen.<\/p>\n <\/div>\n <\/div>\n

\n \n <\/div>\n
\n \n
\n \n \n F\u00f6rderprogramm<\/span>\n
<\/path><\/svg><\/span><\/div>\n
<\/path><\/svg><\/span><\/div>\n <\/a>\n
\n
\n \n
\n \n \n
\n

DFG<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n

\n \n \n Projektpartner<\/span>\n
<\/path><\/svg><\/span><\/div>\n
<\/path><\/svg><\/span><\/div>\n <\/a>\n
\n
\n \n
\n \n \n
<\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n \n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n \n
\n \n
\n
\n \n \n
\n \n
\n \n
\n \n \n

Kontakt<\/h1>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n
\n \n \n
\n \n
\n \n
\n
\n \n \n \"Marius\n
<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n \n
\n \n \n

Prof. Dr. Marius Lindauer<\/h4>\n <\/div>\n <\/div>\n
\n \n \n
\n

Projektkoordinator<\/p>\n <\/div>\n <\/div>\n

\n \n
\n \n
\n
\n \n \n
\n \n
\n \n
<\/path><\/svg><\/span> marius.lindauer@l3s.de<\/span><\/a>\n <\/span>\n <\/div>\n <\/div>\n
\n \n
<\/path><\/svg><\/span> +49 511 762 5301<\/span><\/a>\n <\/span>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n
\n \n \n
\n \n
\n \n
\n
\n \n \n \"Profilbild\"\n
<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n \n
\n \n \n

Dr. Theresa Eimer<\/h4>\n <\/div>\n <\/div>\n
\n \n \n
\n

Projektmanager<\/p>\n <\/div>\n <\/div>\n

\n \n
\n \n
\n
\n \n \n
\n \n
\n \n
<\/path><\/svg><\/span> t.eimer@ai.uni-hannover.de <\/span><\/a>\n <\/span>\n <\/div>\n <\/div>\n
\n \n
<\/path><\/svg><\/span> +49 511 762 17321<\/span><\/a>\n <\/span>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"

Start: 01.01.2025 End: 31.12.2028 Website: – RoGeRL Robust and General Reinforcement Learning via AutoML Reinforcement Learning (RL) enables learning through interaction with the environment. Therefore, it is a component of AI systems for sequential decision-making, e.g., in robotics, in natural sciences such as physics or medicine, or in large language models. However, RL is not […]<\/p>","protected":false},"author":13,"featured_media":39001,"parent":2010,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-templates\/full-width-page.php","meta":{"_acf_changed":false,"footnotes":""},"categories":[],"tags":[198,226,51,26,96],"class_list":["post-39000","page","type-page","status-publish","has-post-thumbnail","hentry","tag-automated-machine-learning","tag-eimer","tag-lindauer","tag-project","tag-science"],"acf":[],"aioseo_notices":[],"publishpress_future_action":{"enabled":true,"date":"2028-12-01 09:00:00","action":"category","newStatus":"draft","terms":[75],"taxonomy":"category","extraData":[]},"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/pages\/39000","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/users\/13"}],"replies":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/comments?post=39000"}],"version-history":[{"count":3,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/pages\/39000\/revisions"}],"predecessor-version":[{"id":39584,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/pages\/39000\/revisions\/39584"}],"up":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/pages\/2010"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/media\/39001"}],"wp:attachment":[{"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/media?parent=39000"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/categories?post=39000"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.l3s.de\/de\/wp-json\/wp\/v2\/tags?post=39000"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}