{"id":502265,"date":"2018-09-04T21:03:07","date_gmt":"2018-09-05T04:03:07","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-event&p=502265"},"modified":"2025-08-06T11:56:52","modified_gmt":"2025-08-06T18:56:52","slug":"reinforcement-learning-day","status":"publish","type":"msr-event","link":"https:\/\/www.microsoft.com\/en-us\/research\/event\/reinforcement-learning-day\/","title":{"rendered":"Reinforcement Learning Day"},"content":{"rendered":"\n\n

Venue:<\/strong> New York University<\/p>\n

Contact:<\/strong> For event questions, please contact msrevent@microsoft.com<\/a>Opens in a new tab<\/span><\/p>\n

Reinforcement Learning Day 2018 will share the latest research on learning to make decisions based on feedback.<\/p>\n

Reinforcement learning is the study of decision making with consequences over time. The topic draws together multi-disciplinary efforts from computer science, cognitive science, mathematics, psychology, economics, control theory, and neuroscience. The common thread through all of these studies is: how do natural and artificial systems learn to make decisions in complex environments based on external, and possibly delayed, feedback.<\/p>\n

This workshop features talks by nine outstanding speakers whose research covers a broad swath of the topic, from statistics to psychology, from computer science to control. A key objective is to bring together the research communities of all these areas to learn from each other and build on the latest knowledge.<\/p>\n

Committee Chairs<\/h3>\n

Hal Daum\u00e9 III (opens in new tab)<\/span><\/a>, Microsoft Research
\nAkshay Krishnamurthy (opens in new tab)<\/span><\/a>, Microsoft Research<\/p>\n

Speakers<\/h3>\n

Shipra Agrawal (opens in new tab)<\/span><\/a>, Columbia University
\nByron Boots (opens in new tab)<\/span><\/a>, Georgia Institute of Technology
\nMarc-Alexandre C\u00f4t\u00e9 (opens in new tab)<\/span><\/a>, Microsoft Research
\nDebadeepta Dey (opens in new tab)<\/span><\/a>, Microsoft Research
\nMiro Dud\u00edk (opens in new tab)<\/span><\/a>, Microsoft Research
\nCatherine Hartley (opens in new tab)<\/span><\/a>, New York University
\nRaia Hadsell (opens in new tab)<\/span><\/a>, Google DeepMind
\nKatja Hofmann (opens in new tab)<\/span><\/a>, Microsoft Research
\nMichael Littman (opens in new tab)<\/span><\/a>, Brown University<\/p>\n

Local Organizer<\/h3>\n

KyungHyun Cho (opens in new tab)<\/span><\/a>, New York University<\/p>\n

Opens in a new tab<\/span><\/p>\n

Monday, September 24, 2018<\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Time (PDT)<\/strong><\/td>\nSession<\/strong><\/td>\n<\/td>\nSpeaker<\/strong><\/td>\n<\/tr>\n
9:00 AM\u20139:10 AM<\/td>\nWelcome<\/td>\n\"Portrait<\/a><\/td>\nJohn Langford<\/strong><\/a>
\nMicrosoft Research NYC<\/td>\n<\/tr>\n
9:10 AM\u20139:55 AM<\/td>\nProgramming Agents via Evaluative Feedback<\/td>\n\"Portrait (opens in new tab)<\/span><\/a><\/td>\nMichael Littman<\/strong> (opens in new tab)<\/span><\/a>
\nBrown University<\/td>\n<\/tr>\n
9:55 AM\u201310:25 AM<\/td>\nDirections and Challenges in Multi-Task Reinforcement Learning<\/td>\n\"Portrait<\/a><\/td>\nKatja Hofmann<\/strong><\/a>
\nMicrosoft Research Cambridge<\/td>\n<\/tr>\n
10:25 AM\u201310:45 AM<\/td>\nBreak<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
10:45 AM\u201311:30 AM<\/td>\n<\/td>\n\"Portrait (opens in new tab)<\/span><\/a><\/td>\nCatherine Hartley<\/strong> (opens in new tab)<\/span><\/a>
\nNew York University<\/td>\n<\/tr>\n
11:30 AM\u201312:15 PM<\/td>\nMachine Learning for Robot Perception, Planning, and Control<\/td>\n\"Portrait (opens in new tab)<\/span><\/a><\/td>\nByron Boots<\/strong> (opens in new tab)<\/span><\/a>
\nGeorgia Institute of Technology<\/td>\n<\/tr>\n
12:15 PM\u20131:45 PM<\/td>\nLunch<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
1:45 PM\u20132:15 PM<\/td>\nImitating the Clairvoyant Oracle: From Information Gathering to Grounded Visual Navigation via Natural Language<\/td>\n\"Portrait<\/a><\/td>\nDebadeepta Dey<\/strong><\/a>
\nMicrosoft Research Redmond<\/td>\n<\/tr>\n
2:15 PM\u20133:00 PM<\/td>\nRepresentation, Memory, and Control: The Challenges of Deep RL in Complex Environments<\/td>\n\"Portrait (opens in new tab)<\/span><\/a><\/td>\nRaia Hadsell<\/strong> (opens in new tab)<\/span><\/a>
\nGoogle DeepMind<\/td>\n<\/tr>\n
3:00 PM\u20133:30 PM<\/td>\nTrying to Solve Text-based Games Using Reinforcement Learning<\/td>\n\"Portrait<\/a><\/td>\nMarc-Alexandre C\u00f4t\u00e9<\/strong><\/a>
\nMicrosoft Research Montr\u00e9al<\/td>\n<\/tr>\n
3:30 PM\u20133:50 PM<\/td>\nBreak<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
3:50 PM\u20134:20 PM<\/td>\nHierarchical Imitation and Reinforcement Learning<\/td>\n\"Portrait<\/a><\/td>\nMiro Dud\u00edk<\/strong><\/a>
\nMicrosoft Research NYC<\/td>\n<\/tr>\n
4:20 PM\u20135:05 PM<\/td>\n<\/td>\n\"Portrait (opens in new tab)<\/span><\/a><\/td>\nShipra Agrawal<\/strong> (opens in new tab)<\/span><\/a>
\nColumbia University<\/td>\n<\/tr>\n
5:05 PM\u20135:15 PM<\/td>\nConcluding Remarks<\/td>\n\"Portrait<\/a><\/td>\nHal Daum\u00e9 III<\/strong><\/a>
\nMicrosoft Research NYC<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Opens in a new tab<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

Reinforcement learning is the problem of building systems that can learn behaviors in an environment, based only on an external reward. At this symposium, we\u2019ll hear from speakers who are experts in a range of topics related to reinforcement learning, from theoretical developments, to real world applications in robotics, healthcare, and beyond.<\/p>\n","protected":false},"featured_media":504785,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr_startdate":"2018-09-24","msr_enddate":"2018-09-24","msr_location":"New York City, NY","msr_expirationdate":"","msr_event_recording_link":"","msr_event_link":"","msr_event_link_redirect":false,"msr_event_time":"9:00 AM\u20135:15 PM","msr_hide_region":false,"msr_private_event":false,"msr_hide_image_in_river":0,"footnotes":""},"research-area":[13556,13547],"msr-region":[197900],"msr-event-type":[197947],"msr-video-type":[],"msr-locale":[268875],"msr-program-audience":[],"msr-post-option":[],"msr-impact-theme":[],"class_list":["post-502265","msr-event","type-msr-event","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-systems-and-networking","msr-region-north-america","msr-event-type-universities","msr-locale-en_us"],"msr_about":"\n\n

Venue:<\/strong> New York University<\/p>\n

Contact:<\/strong> For event questions, please contact msrevent@microsoft.com<\/a>Opens in a new tab<\/span><\/p>\n

Reinforcement Learning Day 2018 will share the latest research on learning to make decisions based on feedback.<\/p>\n

Reinforcement learning is the study of decision making with consequences over time. The topic draws together multi-disciplinary efforts from computer science, cognitive science, mathematics, psychology, economics, control theory, and neuroscience. The common thread through all of these studies is: how do natural and artificial systems learn to make decisions in complex environments based on external, and possibly delayed, feedback.<\/p>\n

This workshop features talks by nine outstanding speakers whose research covers a broad swath of the topic, from statistics to psychology, from computer science to control. A key objective is to bring together the research communities of all these areas to learn from each other and build on the latest knowledge.<\/p>\n

Committee Chairs<\/h3>\n

Hal Daum\u00e9 III (opens in new tab)<\/span><\/a>, Microsoft Research
\nAkshay Krishnamurthy (opens in new tab)<\/span><\/a>, Microsoft Research<\/p>\n

Speakers<\/h3>\n

Shipra Agrawal (opens in new tab)<\/span><\/a>, Columbia University
\nByron Boots (opens in new tab)<\/span><\/a>, Georgia Institute of Technology
\nMarc-Alexandre C\u00f4t\u00e9 (opens in new tab)<\/span><\/a>, Microsoft Research
\nDebadeepta Dey (opens in new tab)<\/span><\/a>, Microsoft Research
\nMiro Dud\u00edk (opens in new tab)<\/span><\/a>, Microsoft Research
\nCatherine Hartley (opens in new tab)<\/span><\/a>, New York University
\nRaia Hadsell (opens in new tab)<\/span><\/a>, Google DeepMind
\nKatja Hofmann (opens in new tab)<\/span><\/a>, Microsoft Research
\nMichael Littman (opens in new tab)<\/span><\/a>, Brown University<\/p>\n

Local Organizer<\/h3>\n

KyungHyun Cho (opens in new tab)<\/span><\/a>, New York University<\/p>\n

Opens in a new tab<\/span><\/p>\n

Monday, September 24, 2018<\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Time (PDT)<\/strong><\/td>\nSession<\/strong><\/td>\n<\/td>\nSpeaker<\/strong><\/td>\n<\/tr>\n
9:00 AM\u20139:10 AM<\/td>\nWelcome<\/td>\n\"Portrait<\/a><\/td>\nJohn Langford<\/strong><\/a>
\nMicrosoft Research NYC<\/td>\n<\/tr>\n
9:10 AM\u20139:55 AM<\/td>\nProgramming Agents via Evaluative Feedback<\/td>\n\"Portrait<\/a><\/td>\nMichael Littman<\/strong><\/a>
\nBrown University<\/td>\n<\/tr>\n
9:55 AM\u201310:25 AM<\/td>\nDirections and Challenges in Multi-Task Reinforcement Learning<\/td>\n\"Portrait<\/a><\/td>\nKatja Hofmann<\/strong><\/a>
\nMicrosoft Research Cambridge<\/td>\n<\/tr>\n
10:25 AM\u201310:45 AM<\/td>\nBreak<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
10:45 AM\u201311:30 AM<\/td>\n<\/td>\n\"Portrait<\/a><\/td>\nCatherine Hartley<\/strong><\/a>
\nNew York University<\/td>\n<\/tr>\n
11:30 AM\u201312:15 PM<\/td>\nMachine Learning for Robot Perception, Planning, and Control<\/td>\n\"Portrait<\/a><\/td>\nByron Boots<\/strong><\/a>
\nGeorgia Institute of Technology<\/td>\n<\/tr>\n
12:15 PM\u20131:45 PM<\/td>\nLunch<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
1:45 PM\u20132:15 PM<\/td>\nImitating the Clairvoyant Oracle: From Information Gathering to Grounded Visual Navigation via Natural Language<\/td>\n\"Portrait<\/a><\/td>\nDebadeepta Dey<\/strong><\/a>
\nMicrosoft Research Redmond<\/td>\n<\/tr>\n
2:15 PM\u20133:00 PM<\/td>\nRepresentation, Memory, and Control: The Challenges of Deep RL in Complex Environments<\/td>\n\"Portrait<\/a><\/td>\nRaia Hadsell<\/strong><\/a>
\nGoogle DeepMind<\/td>\n<\/tr>\n
3:00 PM\u20133:30 PM<\/td>\nTrying to Solve Text-based Games Using Reinforcement Learning<\/td>\n\"Portrait<\/a><\/td>\nMarc-Alexandre C\u00f4t\u00e9<\/strong><\/a>
\nMicrosoft Research Montr\u00e9al<\/td>\n<\/tr>\n
3:30 PM\u20133:50 PM<\/td>\nBreak<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
3:50 PM\u20134:20 PM<\/td>\nHierarchical Imitation and Reinforcement Learning<\/td>\n\"Portrait<\/a><\/td>\nMiro Dud\u00edk<\/strong><\/a>
\nMicrosoft Research NYC<\/td>\n<\/tr>\n
4:20 PM\u20135:05 PM<\/td>\n<\/td>\n\"Portrait<\/a><\/td>\nShipra Agrawal<\/strong><\/a>
\nColumbia University<\/td>\n<\/tr>\n
5:05 PM\u20135:15 PM<\/td>\nConcluding Remarks<\/td>\n\"Portrait<\/a><\/td>\nHal Daum\u00e9 III<\/strong><\/a>
\nMicrosoft Research NYC<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Opens in a new tab<\/span><\/p>\n","tab-content":[{"id":0,"name":"About","content":"Reinforcement Learning Day 2018 will share the latest research on learning to make decisions based on feedback.\r\n\r\nReinforcement learning is the study of decision making with consequences over time. The topic draws together multi-disciplinary efforts from computer science, cognitive science, mathematics, psychology, economics, control theory, and neuroscience. The common thread through all of these studies is: how do natural and artificial systems learn to make decisions in complex environments based on external, and possibly delayed, feedback.\r\n\r\nThis workshop features talks by nine outstanding speakers whose research covers a broad swath of the topic, from statistics to psychology, from computer science to control. A key objective is to bring together the research communities of all these areas to learn from each other and build on the latest knowledge.\r\n

Committee Chairs<\/h3>\r\n

Hal Daum\u00e9 III<\/a>, Microsoft Research\r\nAkshay Krishnamurthy<\/a>, Microsoft Research<\/p>\r\n\r\n

Speakers<\/h3>\r\n

Shipra Agrawal<\/a>, Columbia University\r\nByron Boots<\/a>, Georgia Institute of Technology\r\nMarc-Alexandre C\u00f4t\u00e9<\/a>, Microsoft Research\r\nDebadeepta Dey<\/a>, Microsoft Research\r\nMiro Dud\u00edk<\/a>, Microsoft Research\r\nCatherine Hartley<\/a>, New York University\r\nRaia Hadsell<\/a>, Google DeepMind\r\nKatja Hofmann<\/a>, Microsoft Research\r\nMichael Littman<\/a>, Brown University<\/p>\r\n\r\n

Local Organizer<\/h3>\r\n

KyungHyun Cho<\/a>, New York University<\/p>"},{"id":1,"name":"Agenda","content":"

Monday, September 24, 2018<\/h2>\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n
Time (PDT)<\/strong><\/td>\r\nSession<\/strong><\/td>\r\n<\/td>\r\nSpeaker<\/strong><\/td>\r\n<\/tr>\r\n
9:00 AM\u20139:10 AM<\/td>\r\nWelcome<\/td>\r\n\"Portrait<\/a><\/td>\r\nJohn Langford<\/strong><\/a>\r\nMicrosoft Research NYC<\/td>\r\n<\/tr>\r\n
9:10 AM\u20139:55 AM<\/td>\r\nProgramming Agents via Evaluative Feedback<\/td>\r\n\"Portrait<\/a><\/td>\r\nMichael Littman<\/strong><\/a>\r\nBrown University<\/td>\r\n<\/tr>\r\n
9:55 AM\u201310:25 AM<\/td>\r\nDirections and Challenges in Multi-Task Reinforcement Learning<\/td>\r\n\"Portrait<\/a><\/td>\r\nKatja Hofmann<\/strong><\/a>\r\nMicrosoft Research Cambridge<\/td>\r\n<\/tr>\r\n
10:25 AM\u201310:45 AM<\/td>\r\nBreak<\/td>\r\n<\/td>\r\n<\/td>\r\n<\/tr>\r\n
10:45 AM\u201311:30 AM<\/td>\r\n<\/td>\r\n\"Portrait<\/a><\/td>\r\nCatherine Hartley<\/strong><\/a>\r\nNew York University<\/td>\r\n<\/tr>\r\n
11:30 AM\u201312:15 PM<\/td>\r\nMachine Learning for Robot Perception, Planning, and Control<\/td>\r\n\"Portrait<\/a><\/td>\r\nByron Boots<\/strong><\/a>\r\nGeorgia Institute of Technology<\/td>\r\n<\/tr>\r\n
12:15 PM\u20131:45 PM<\/td>\r\nLunch<\/td>\r\n<\/td>\r\n<\/td>\r\n<\/tr>\r\n
1:45 PM\u20132:15 PM<\/td>\r\nImitating the Clairvoyant Oracle: From Information Gathering to Grounded Visual Navigation via Natural Language<\/td>\r\n\"Portrait<\/a><\/td>\r\nDebadeepta Dey<\/strong><\/a>\r\nMicrosoft Research Redmond<\/td>\r\n<\/tr>\r\n
2:15 PM\u20133:00 PM<\/td>\r\nRepresentation, Memory, and Control: The Challenges of Deep RL in Complex Environments<\/td>\r\n\"Portrait<\/a><\/td>\r\nRaia Hadsell<\/strong><\/a>\r\nGoogle DeepMind<\/td>\r\n<\/tr>\r\n
3:00 PM\u20133:30 PM<\/td>\r\nTrying to Solve Text-based Games Using Reinforcement Learning<\/td>\r\n\"Portrait<\/a><\/td>\r\nMarc-Alexandre C\u00f4t\u00e9<\/strong><\/a>\r\nMicrosoft Research Montr\u00e9al<\/td>\r\n<\/tr>\r\n
3:30 PM\u20133:50 PM<\/td>\r\nBreak<\/td>\r\n<\/td>\r\n<\/td>\r\n<\/tr>\r\n
3:50 PM\u20134:20 PM<\/td>\r\nHierarchical Imitation and Reinforcement Learning<\/td>\r\n\"Portrait<\/a><\/td>\r\nMiro Dud\u00edk<\/strong><\/a>\r\nMicrosoft Research NYC<\/td>\r\n<\/tr>\r\n
4:20 PM\u20135:05 PM<\/td>\r\n<\/td>\r\n\"Portrait<\/a><\/td>\r\nShipra Agrawal<\/strong><\/a>\r\nColumbia University<\/td>\r\n<\/tr>\r\n
5:05 PM\u20135:15 PM<\/td>\r\nConcluding Remarks<\/td>\r\n\"Portrait<\/a><\/td>\r\nHal Daum\u00e9 III<\/strong><\/a>\r\nMicrosoft Research NYC<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>"}],"msr_startdate":"2018-09-24","msr_enddate":"2018-09-24","msr_event_time":"9:00 AM\u20135:15 PM","msr_location":"New York City, NY","msr_event_link":"","msr_event_recording_link":"","msr_startdate_formatted":"September 24, 2018","msr_register_text":"Watch now","msr_cta_link":"","msr_cta_text":"","msr_cta_bi_name":"","featured_image_thumbnail":"\"Reinforcement","event_excerpt":"Reinforcement learning is the problem of building systems that can learn behaviors in an environment, based only on an external reward. At this symposium, we\u2019ll hear from speakers who are experts in a range of topics related to reinforcement learning, from theoretical developments, to real world applications in robotics, healthcare, and beyond.","msr_research_lab":[199565,199571,437514],"related-researchers":[{"type":"user_nicename","display_name":"Katja Hofmann","user_id":32468,"people_section":"Section name 1","alias":"kahofman"},{"type":"user_nicename","display_name":"Marc-Alexandre C\u00f4t\u00e9","user_id":37197,"people_section":"Section name 1","alias":"macote"},{"type":"user_nicename","display_name":"Miro Dud\u00edk","user_id":32867,"people_section":"Section name 1","alias":"mdudik"},{"type":"user_nicename","display_name":"John Langford","user_id":32204,"people_section":"Section name 1","alias":"jcl"}],"msr_impact_theme":[],"related-academic-programs":[],"related-groups":[395930],"related-projects":[],"related-opportunities":[],"related-publications":[],"related-videos":[],"related-posts":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/502265","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-event"}],"version-history":[{"count":5,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/502265\/revisions"}],"predecessor-version":[{"id":1147079,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event\/502265\/revisions\/1147079"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/504785"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=502265"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=502265"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=502265"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=502265"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=502265"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=502265"},{"taxonomy":"msr-program-audience","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-program-audience?post=502265"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=502265"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=502265"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}