{"id":589297,"date":"2019-03-26T00:00:21","date_gmt":"2019-03-26T07:00:21","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/?post_type=msr-research-item&#038;p=589297"},"modified":"2019-05-22T14:16:29","modified_gmt":"2019-05-22T21:16:29","slug":"successor-uncertainties-exploration-and-uncertainty-in-temporal-difference-learning","status":"publish","type":"msr-video","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/video\/successor-uncertainties-exploration-and-uncertainty-in-temporal-difference-learning\/","title":{"rendered":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning"},"content":{"rendered":"<p>Probabilistic Q-learning is a promising approach balancing exploration and exploitation in reinforcement learning.<br \/>\nHowever, existing implementations have significant limitations: they either fail to incorporate uncertainty about long-term consequences of actions or ignore fundamental dependencies in state-action values implied by the~Bellman equation. These problems result in sub-optimal exploration. As a solution, we develop Successor Uncertainties (SU), a probabilistic Q-learning method free of the aforementioned problems. SU outperforms existing baselines on tabular problems and on the Atari benchmark benchmark suite. Overall, SU is an improved and scalable probabilistic Q-learning method with better properties than its predecessors at no extra cost.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Probabilistic Q-learning is a promising approach balancing exploration and exploitation in reinforcement learning. However, existing implementations have significant limitations: they either fail to incorporate uncertainty about long-term consequences of actions or ignore fundamental dependencies in state-action values implied by the~Bellman equation. These problems result in sub-optimal exploration. As a solution, we develop Successor Uncertainties (SU), [&hellip;]<\/p>\n","protected":false},"featured_media":589303,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_hide_image_in_river":0,"footnotes":""},"research-area":[13556],"msr-video-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-session-type":[],"msr-impact-theme":[],"msr-pillar":[],"msr-episode":[],"msr-research-theme":[],"class_list":["post-589297","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/jOEhYByjx10","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/589297","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/589297\/revisions"}],"predecessor-version":[{"id":589300,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/589297\/revisions\/589300"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media\/589303"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=589297"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=589297"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=589297"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=589297"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=589297"},{"taxonomy":"msr-session-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-session-type?post=589297"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=589297"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=589297"},{"taxonomy":"msr-episode","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-episode?post=589297"},{"taxonomy":"msr-research-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-theme?post=589297"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}