{"id":794111,"date":"2021-11-16T08:00:45","date_gmt":"2021-11-16T16:00:45","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=794111"},"modified":"2021-11-09T15:57:26","modified_gmt":"2021-11-09T23:57:26","slug":"research-talk-breaking-the-deadly-triad-with-a-target-network","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/research-talk-breaking-the-deadly-triad-with-a-target-network\/","title":{"rendered":"Research talk: Breaking the deadly triad with a target network"},"content":{"rendered":"<p>The deadly triad refers to the instability of an off-policy reinforcement learning (RL) algorithm when it employs function approximation and bootstrapping simultaneously, and this is a major challenge in off-policy RL. Join PhD student Shangtong Zhang, from the WhiRL group at the University of Oxford, to learn how the target network can be used as a tool for theoretically breaking the deadly triad. Together, you&#8217;ll explore how to theoretically understand the conventional wisdom that a target network stabilizes training, a novel target network update rule that augments the commonly used Polyak-averaging style update with two projections, and how a target network can be used in linear off-policy RL algorithms, in both prediction and control settings, as well as both discounted and average-reward Markov decision processes.<\/p>\n<p>Learn more about the 2021 Microsoft Research Summit: <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/Aka.ms\/researchsummit\">https:\/\/Aka.ms\/researchsummit<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The deadly triad refers to the instability of an off-policy reinforcement learning (RL) algorithm when it employs function approximation and bootstrapping simultaneously, and this is a major challenge in off-policy RL. Join PhD student Shangtong Zhang, from the WhiRL group at the University of Oxford, to learn how the target network can be used as [&hellip;]<\/p>\n","protected":false},"featured_media":794114,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-video-type":[261263,261311],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-794111","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-video-type-research-summit-2021","msr-video-type-reinforcement-learning","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/4QxrLGsNj5I","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/794111"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/794111\/revisions"}],"predecessor-version":[{"id":794120,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/794111\/revisions\/794120"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/794114"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=794111"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=794111"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=794111"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=794111"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=794111"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=794111"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=794111"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}