2018年9月24日
Reinforcement Learning Day
9:00 AM–5:15 PM
地点： New York City, NY
Monday, September 24, 2018
| Time (PDT) | Session | Speaker | |
| 9:00 AM–9:10 AM | Welcome |  |
John Langford Microsoft Research NYC |
| 9:10 AM–9:55 AM | Programming Agents via Evaluative Feedback |  |
Michael Littman Brown University |
| 9:55 AM–10:25 AM | Directions and Challenges in Multi-Task Reinforcement Learning |  |
Katja Hofmann Microsoft Research Cambridge |
| 10:25 AM–10:45 AM | Break | ||
| 10:45 AM–11:30 AM |  |
Catherine Hartley New York University |
|
| 11:30 AM–12:15 PM | Machine Learning for Robot Perception, Planning, and Control |  |
Byron Boots Georgia Institute of Technology |
| 12:15 PM–1:45 PM | Lunch | ||
| 1:45 PM–2:15 PM | Imitating the Clairvoyant Oracle: From Information Gathering to Grounded Visual Navigation via Natural Language |  |
Debadeepta Dey Microsoft Research Redmond |
| 2:15 PM–3:00 PM | Representation, Memory, and Control: The Challenges of Deep RL in Complex Environments |  |
Raia Hadsell Google DeepMind |
| 3:00 PM–3:30 PM | Trying to Solve Text-based Games Using Reinforcement Learning |  |
Marc-Alexandre Côté Microsoft Research Montréal |
| 3:30 PM–3:50 PM | Break | ||
| 3:50 PM–4:20 PM | Hierarchical Imitation and Reinforcement Learning |  |
Miro Dudík Microsoft Research NYC |
| 4:20 PM–5:05 PM |  |
Shipra Agrawal Columbia University |
|
| 5:05 PM–5:15 PM | Concluding Remarks |  |
Hal Daumé III Microsoft Research NYC |