Skip to content Skip to navigation

About

Welcome to the website for the Stanford RL (Reinforcement Learning) Forum.

We hope to develop a growing community of researchers in both industry and academia that are interested in reinforcement learning. With connections to control theory, operations research, computer science, statistics, and many more fields this may include a lot of people!

Details of the upcoming talks will be posted in the talks section. Also, subscribe to the mailing list here.
 
The RL Forum is sponsored by the Stanford Computer Forum.
 
 
RL Forum talks:
Temporal Abstraction in Reinforcement Learning with the Successor Representation (Marlos Machado 2:00 PM - 3:00 PM, Feb 25, 2020 (Tuesday) Packard 202
From Reinforcement Learning to Stochastic Optimization: A Universal Framework for Sequential Decision Analytics (Warren Powell) 4:30 PM - 5:30 PM, Jan 29, 2020 (Wednesday) Shriram 262
Representation, Modeling, and Optimization in Reinforcement Learning (Sham Kakade) 4:30 PM - 5:30 PM, Jan 22, 2020 (Wednesday) 200 - 034
Do Deep Generative Models Know What They Don't Know? (Balaji Lakshminarayanan) 4:00 PM - 5:00 PM,  May 28, 2019 (Tuesday) Packard 101
Reinforcement Learning and Optimal Control: An Overview (Dimitri P. Bertsekas) 4:00 PM - 5:00 PM, March 4, 2019 (Monday) Packard 101
4:15 PM - 5:15 PM, Nov 13, 2018 (Tuesday) Packard 202
Is Q-learning Provably Efficient? (Chi Jin) 3:15 PM - 4:15 PM, Oct 12, 2018 (Friday)  Packard 202

 

 

Talks

 

Temporal Abstraction in Reinforcement Learning with the Successor Representation 

Marlos Machado

Research scientist
Google Brain
Montreal

Location: Packard 202
Time: 2:00 PM - 3:00 PM, Tuesday, February 25

Contact us

If you have any comments, questions or suggestions please feel free to get in touch with an organizing member.

For organizational or site-specific problems please reach out to sdong15 or vikranth "at" stanford "dot" edu.

You can subscribe to the mailing list here.

 
Subscribe to Stanford RL Forum RSS