Beyond Worst-Case: Instance-Dependent Optimality in Reinforcement Learning
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=RZzgCqgClvw
Martin Wainwright (UC Berkeley)
https://simons.berkeley.edu/talks/tbd-236
Reinforcement Learning from Batch Data and Simulation
Other Videos By Simons Institute for the Theory of Computing
Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Reinforcement Learning from Batch Data and Simulation
Martin Wainwright