{"id":142,"date":"2024-02-27T15:26:21","date_gmt":"2024-02-27T15:26:21","guid":{"rendered":"https:\/\/wp.lancs.ac.uk\/colab\/?p=142"},"modified":"2025-02-27T15:34:20","modified_gmt":"2025-02-27T15:34:20","slug":"receps-reward-certification-for-policy-smoothed-reinforcement-learning","status":"publish","type":"post","link":"https:\/\/wp.lancs.ac.uk\/colab\/2024\/02\/27\/receps-reward-certification-for-policy-smoothed-reinforcement-learning\/","title":{"rendered":"ReCePS: Reward Certification for Policy Smoothed Reinforcement Learning"},"content":{"rendered":"<p><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/wp.lancs.ac.uk\/colab\/files\/2025\/02\/receps.png\" alt=\"\" width=\"994\" height=\"850\" class=\"aligncenter size-full wp-image-143\" srcset=\"https:\/\/wp.lancs.ac.uk\/colab\/files\/2025\/02\/receps.png 994w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2025\/02\/receps-300x257.png 300w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2025\/02\/receps-768x657.png 768w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2025\/02\/receps-676x578.png 676w\" sizes=\"auto, (max-width: 994px) 100vw, 994px\" \/><br \/>\nWe presented the paper &#8220;ReCePS: Reward Certification for Policy Smoothed Reinforcement Learning&#8221;, at the AAAI Conference on Artificial Intelligence (AAAI 2024). Our work introduces a certification method for smoothed policies, which are more robust than traditional policies in reinforcement learning. We presented a more general certification method than the previous state-of-the-art, using a black-box approach. Our paper is <a href=\"https:\/\/www.research.lancs.ac.uk\/portal\/services\/downloadRegister\/403063640\/5103_AAAI_1.pdf\">freely available<\/a>. The source code is also <a href=\"https:\/\/github.com\/TrustAI\/ReCePS\">available<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We presented the paper &#8220;ReCePS: Reward Certification for Policy Smoothed Reinforcement Learning&#8221;, at the AAAI Conference on Artificial Intelligence (AAAI 2024). Our work introduces a certification method for smoothed policies, which are more robust than traditional policies in reinforcement learning. We presented a more general certification method than the previous state-of-the-art, using a black-box approach. [&hellip;]<\/p>\n","protected":false},"author":1432,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3],"tags":[],"class_list":["post-142","post","type-post","status-publish","format-standard","hentry","category-news"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/142","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/users\/1432"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/comments?post=142"}],"version-history":[{"count":1,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/142\/revisions"}],"predecessor-version":[{"id":144,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/142\/revisions\/144"}],"wp:attachment":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/media?parent=142"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/categories?post=142"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/tags?post=142"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}