Online Learning in MDPs (Part 1)

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=0_u-6NrWIu8


Duration: 1:25:37
2,547 views
42

Ambuj Tewari (University of Michigan)
https://simons.berkeley.edu/talks/tbd-183
Theory of Reinforcement Learning Boot Camp



Other Videos By Simons Institute for the Theory of Computing


2020-09-03Control Fundamentals
2020-09-02Learning to Act from Observations
2020-09-02Statistical Considerations in Reinforcement Learning (Part 2b)...
2020-09-02Statistical Considerations in Reinforcement Learning (Part 2a)...
2020-09-02Statistical Considerations in Reinforcement Learning (Part 1b):..
2020-09-02Statistical Considerations in Reinforcement Learning (Part 1a):..
2020-09-01The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
2020-09-01Batch (Offline) RL (Part 2)
2020-09-01Batch (Offline) RL (Part 1)
2020-09-01Online Learning in MDPs (Part 2)
2020-09-01Online Learning in MDPs (Part 1)
2020-08-31Optimizing Intended Reward Functions: Extracting All the Right Information From All the Right Places
2020-08-31Online Learning and Bandits (Part 2)
2020-08-31Recent Progress in High-Dimensional Learning
2020-08-31Online Learning and Bandits (Part 1)
2020-08-31Planning and Markov Decision Processes (Part 2)
2020-08-28Statistical Physics and Computation in High Dimension
2020-08-28Statistical Physics and Computation in High Dimension
2020-08-27Recent Progress in High-Dimensional Learning
2020-08-26Sketching High-Dimensional Data
2020-08-26Recent Progress in High-Dimensional Learning


Tags:
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Theory of Reinforcement Learning Boot Camp
Ambuj Tewari