{"id":1405,"date":"2023-10-17T13:31:32","date_gmt":"2023-10-17T13:31:32","guid":{"rendered":"https:\/\/dataninja.nrw\/?p=1405"},"modified":"2023-10-17T18:14:16","modified_gmt":"2023-10-17T18:14:16","slug":"11-10-23-rl%c2%b3-wins-best-paper-award-at-lod-2023","status":"publish","type":"post","link":"https:\/\/dataninja.nrw\/?p=1405","title":{"rendered":"11.10.23: (RL)\u00b3 wins best paper award at LOD 2023"},"content":{"rendered":"\n<p>Moritz Lange (Institute for Neural Computation, Ruhr-University Bochum) and Raphael Engelhardt (Cologne Institute of Computer Science, TH K\u00f6ln) won the Best Paper Award at the 9<sup>th<\/sup>&nbsp;International Conference on Machine&nbsp;Learning,&nbsp;Optimization, and&nbsp;Data Science (LOD 2023) for their work <em>\u201cImproving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison\u201d<\/em>. Their research carries significant implications for practical reinforcement learning (RL) applications in various industries.<br><br><strong>Notable Findings:<\/strong><\/p>\n\n\n\n<ul>\n<li>The study is the first to empirically compare various conventional representation learning approaches for reinforcement learning in a systematical way.<\/li>\n\n\n\n<li>Their research underscores the importance of learning environment dynamics as a key factor for enhancing RL performance. This is obtained by introducing an auxiliary task to the original task of optimizing RL rewards.<\/li>\n<\/ul>\n\n\n\n<p>These groundbreaking insights open the door to more efficient and practical RL solutions, particularly in environments where visual observations are limited. <br><br>Congratulations to Moritz and Raphael!<br><br><strong>Full reference:<\/strong><br>Lange, M., Krystiniak, N., Engelhardt, R. C., Konen, W., &amp; Wiskott, L. (2023). Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison.<br><a href=\"https:\/\/arxiv.org\/abs\/2310.04241v2\">Click to show paper on arXiv  <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Moritz Lange (Institute for Neural Computation, Ruhr-University Bochum) and Raphael Engelhardt (Cologne Institute of Computer Science, TH K\u00f6ln) won the [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":1406,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ub_ctt_via":"","footnotes":""},"categories":[1],"tags":[],"featured_image_src":"https:\/\/dataninja.nrw\/wp-content\/uploads\/2023\/10\/02_RL3_A3_vs3-scaled.jpg","author_info":{"display_name":"admin","author_link":"https:\/\/dataninja.nrw\/?author=1"},"_links":{"self":[{"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/posts\/1405"}],"collection":[{"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1405"}],"version-history":[{"count":2,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/posts\/1405\/revisions"}],"predecessor-version":[{"id":1409,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/posts\/1405\/revisions\/1409"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=\/wp\/v2\/media\/1406"}],"wp:attachment":[{"href":"https:\/\/dataninja.nrw\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1405"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1405"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dataninja.nrw\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1405"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}