{"id":587173,"date":"2019-04-11T00:00:38","date_gmt":"2019-04-11T07:00:38","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=587173"},"modified":"2019-05-16T16:33:08","modified_gmt":"2019-05-16T23:33:08","slug":"deep-policy-gradient-algorithms-a-closer-look","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/deep-policy-gradient-algorithms-a-closer-look\/","title":{"rendered":"Deep Policy Gradient Algorithms: A Closer Look"},"content":{"rendered":"<p>Deep reinforcement learning methods are behind some of the most publicized recent results in machine learning. In spite of these successes, however, deep RL methods face a number of systemic issues: brittleness to small changes in hyperparameters, high reward variance across runs, and sensitivity to seemingly small algorithmic changes.<\/p>\n<p>In this talk we take a closer look at the potential root of these issues. Specifically, we study how the policy gradient primitives underlying popular deep RL algorithms reflect the principles informing their development.<\/p>\n<p><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/05\/Deep-Policy-Gradient-Algorithms-A-Closer-Look-slides.pdf\" target=\"_blank\" rel=\"noopener noreferrer\">[SLIDES]<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Deep reinforcement learning methods are behind some of the most publicized recent results in machine learning. In spite of these successes, however, deep RL methods face a number of systemic issues: brittleness to small changes in hyperparameters, high reward variance across runs, and sensitivity to seemingly small algorithmic changes. In this talk we take a [&hellip;]<\/p>\n","protected":false},"featured_media":588187,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13561,13546],"msr-video-type":[206954],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-587173","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-algorithms","msr-research-area-computational-sciences-mathematics","msr-video-type-microsoft-research-talks","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/7J2zajQe7lw","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/587173"}],"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":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/587173\/revisions"}],"predecessor-version":[{"id":587191,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/587173\/revisions\/587191"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/588187"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=587173"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=587173"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=587173"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=587173"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=587173"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=587173"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}