Workshops

Fall 2020

Theory of Reinforcement Learning Boot Camp

Aug 31, 2020 to Sep 4, 2020

Return to event »

Times are listed in Pacific Time.

Monday, August 31st, 2020
8:50 am–9:00 am		Opening Remarks
9:00 am–10:00 am		Planning and Markov Decision Processes (Part 1) Csaba Szepesvari (University of Alberta, Google DeepMind) & Mengdi Wang (Princeton University, Google DeepMind)
10:00 am–10:30 am		Break
10:30 am–11:30 am		Planning and Markov Decision Processes (Part 2) Csaba Szepesvari (University of Alberta, Google DeepMind) & Mengdi Wang (Princeton University, Google DeepMind)
11:30 am–12:30 pm		Lunch
12:30 pm–1:30 pm		Online Learning and Bandits (Part 1) Alan Malek (DeepMind) & Wouter Koolen (Centrum Wiskunde & Informatica)
1:30 pm–2:00 pm		Break
2:00 pm–3:00 pm		Online Learning and Bandits (Part 2) Alan Malek (DeepMind) & Wouter Koolen (Centrum Wiskunde & Informatica)
3:00 pm–3:30 pm		Coffee Break
3:30 pm–4:30 pm		Optimizing Intended Reward Functions: Extracting All the Right Information From All the Right Places Anca Dragan (UC Berkeley)

Tuesday, September 1st, 2020
9:00 am–10:00 am		Online Learning in MDPs (Part 1) Ambuj Tewari (University of Michigan)
10:00 am–10:30 am		Break
10:30 am–11:30 am		Online Learning in MDPs (Part 2) Gergely Neu (UPF)
11:30 am–12:30 pm		Lunch
12:30 pm–1:30 pm		Batch (Offline) RL (Part 1) Emma Brunskill (Stanford University)
1:30 pm–2:00 pm		Break
2:00 pm–3:00 pm		Batch (Offline) RL (Part 2) Emma Brunskill (Stanford University)
3:00 pm–3:30 pm		Coffee Break
3:30 pm–4:30 pm		The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies Stephan Zheng (Salesforce Research)

Wednesday, September 2nd, 2020
9:00 am–10:00 am		Statistical Considerations in Reinforcement Learning (Part 1): Statistical Inference and Non-Regularity Eric Laber (North Carolina State University)
10:00 am–10:30 am		Break
10:30 am–11:30 am		Statistical Considerations in Reinforcement Learning (Part 1): Statistical Inference and Non-Regularity Eric Laber (North Carolina State University)
11:30 am–12:30 pm		Lunch
12:30 pm–1:30 pm		Statistical Considerations in Reinforcement Learning (Part 2): Emerging Application Areas and Challenges Eric Laber (North Carolina State University)
1:30 pm–2:00 pm		Break
2:00 pm–3:00 pm		Statistical Considerations in Reinforcement Learning (Part 2): Emerging Application Areas and Challenges Eric Laber (North Carolina State University)
3:00 pm–3:30 pm		Coffee Break
3:30 pm–4:30 pm		Learning to Act from Observations Ashley Edwards (Georgia Tech)

Thursday, September 3rd, 2020
9:00 am–10:00 am		Control Fundamentals Sean Meyn (University of Florida)
10:00 am–10:30 am		Break
10:30 am–11:30 am		Every Optimization Problem Is a Quadratic Program: Applications to Dynamic Programming and Q-Learning Sean Meyn (University of Florida)
11:30 am–12:30 pm		Lunch
12:30 pm–1:30 pm		Basics of Algorithm Design and Analysis Sean Meyn (University of Florida)
1:30 pm–2:00 pm		Break
2:00 pm–3:00 pm		Recent Results on RL With Gradient Free Optimization Sean Meyn (University of Florida)
3:00 pm–3:30 pm		Coffee Break
3:30 pm–4:30 pm		Gradient-Free Optimization With Applications to Power Systems Andrey Bernstein (National Renewable Energy Laboratory)

Friday, September 4th, 2020
9:00 am–10:00 am		Stochastic Programming Approach to Optimization Under Uncertainty (Part 1) Alex Shapiro (Georgia Tech)
10:00 am–10:30 am		Break
10:30 am–11:30 am		Stochastic Programming Approach to Optimization Under Uncertainty (Part 2) Alex Shapiro (Georgia Tech)
11:30 am–12:30 pm		Lunch
12:30 pm–1:30 pm		Simulation Methodology: An Overview (Part 1) Peter Glynn (Stanford)
1:30 pm–2:00 pm		Break
2:00 pm–3:00 pm		Simulation Methodology: An Overview (Part 2) Peter Glynn (Stanford)
3:00 pm–3:30 pm		Coffee Break
3:30 pm–4:30 pm		A Few Challenge Problems from Robotics Russ Tedrake (MIT & Toyota Research Institute)