October 3, 2019
Reinforcement Learning Day 2019
Lieu: New York, NY
All registered guests must check-in at the Microsoft Welcome Center (entrance on 8th Avenue between 41st and 42nd Streets) on the day of the event with a government-issued photo ID to receive an elevator pass. Please plan on arriving 15 minutes early to ensure you have enough time to acquire the requisite pass/badge.
Thursday, October 3, 2019
| Time (PDT) | Session | Speaker | |
| 8:00 AM | Breakfast | ||
| 9:00 AM | Welcome | ||
| 9:10 AM | Reward Machines: Structuring reward function specifications and reducing sample complexity in reinforcement learning | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Sheila McIlraith (opens in new tab), University of Toronto |
| 9:50 AM | Generalization in Reinforcement Learning with Selective Noise Injection | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Sam Devlin (opens in new tab), MSR Cambridge |
| 10:15 AM | Break | ||
| 10:45 AM | Scalable and Robust Multi-Agent Reinforcement Learning | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Christopher Amato (opens in new tab), Northeastern University |
| 11:25 AM | Reinforcement Learning From Small Data In Feature Space | video (opens in new tab) |  (opens in new tab) |
Mengdi Wang (opens in new tab), Princeton University |
| 12:05 PM | Lunch | ||
| 2:05 PM | Safe and Fair Reinforcement Learning | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Philip Thomas (opens in new tab), University of Massachusetts, Amherst |
| 2:45 PM | Grounding Natural Language for Embodied Agents | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Asli Celikyilmaz (opens in new tab), MSR Redmond |
| 3:10 PM | Break | ||
| 3:40 PM | Learning for policy improvement | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Geoff Gordon (opens in new tab), MSR Montréal |
| 4:05 PM | Towards Using Batch Reinforcement Learning to Identify Treatment Options in Healthcare | slides (opens in new tab) | video (opens in new tab) |  (opens in new tab) |
Finale Doshi-Velez (opens in new tab), Harvard University |
| 4:45 PM | Concluding remarks | ||
| 5:00 PM | End of day |