{"id":425502,"date":"2017-09-18T12:13:54","date_gmt":"2017-09-18T19:13:54","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=425502"},"modified":"2021-10-14T21:28:49","modified_gmt":"2021-10-15T04:28:49","slug":"deep-reinforcement-learning-for-operational-optimal-control","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/deep-reinforcement-learning-for-operational-optimal-control\/","title":{"rendered":"Model-based Reinforcement Learning for Control Problems"},"content":{"rendered":"<p>This research project aims at developing a new class of Reinforcement Learning (RL) algorithms that are sample efficient, off policy, and transferable. We seek to demonstrate these new algorithms in real-world operational optimal control applications such as<\/p>\n<p><strong>Indoor Farm Control<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-553701\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/09\/897407587-1024x681.jpeg\" alt=\"Greenhouse\" width=\"464\" height=\"309\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/09\/897407587-1024x681.jpeg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/09\/897407587-300x200.jpeg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/09\/897407587-768x511.jpeg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/09\/897407587.jpeg 2000w\" sizes=\"(max-width: 464px) 100vw, 464px\" \/>\u00a0 \u00a0<img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-553716\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2017\/09\/OBT-1024x683.jpg\" alt=\"\" width=\"465\" height=\"308\" \/><\/p>\n<p><strong>Data Center Energy Consumption Optimization<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone\" src=\"https:\/\/cnet3.cbsistatic.com\/img\/uuUcbOkQ8f27EJYfE8pzasyGo_o=\/936x527\/2009\/10\/07\/10556205-f0fe-11e2-8c7c-d4ae52e62bcc\/CH1245.jpg\" alt=\"Data center\" width=\"465\" height=\"262\" \/><\/p>\n<h2>News<\/h2>\n<ul>\n<li>Microsoft Asia News Center covers our research in <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/news.microsoft.com\/apac\/features\/indoor-vertical-farming-digging-deep-data\/\">indoor vertical farming<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>This research project aims at developing a new class of Reinforcement Learning (RL) algorithms that are sample efficient, off policy, and transferable. We seek to demonstrate these new algorithms in real-world operational optimal control applications such as Indoor Farm Control \u00a0 \u00a0 Data Center Energy Consumption Optimization News Microsoft Asia News Center covers our research [&hellip;]<\/p>\n","protected":false},"featured_media":470274,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13547],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-425502","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-systems-and-networking","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2017-08-01","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Chetan Bansal","user_id":31394,"people_section":"Section name 1","alias":"chetanb"},{"type":"user_nicename","display_name":"Ranveer Chandra","user_id":33344,"people_section":"Section name 1","alias":"ranveer"}],"msr_research_lab":[199565],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/425502"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":12,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/425502\/revisions"}],"predecessor-version":[{"id":553725,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/425502\/revisions\/553725"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/470274"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=425502"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=425502"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=425502"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=425502"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=425502"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}