Sample-Efficient Reinforcement Learning with Rich Observations

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=L5Q4Y3omnrY


Duration: 58:48
1,649 views
26

Alekh Agarwal, Microsoft Research New York
https://simons.berkeley.edu/talks/alekh-agarwal-02-15-2017
Interactive Learning



Other Videos By Simons Institute for the Theory of Computing


2017-02-17TicToc: A General Technique for Near-Optimal Active Learning with Noise
2017-02-17Systems Presentation
2017-02-17Active Nearest-Neighbor Learning in Metric Spaces
2017-02-17Hierarchical Learning for Human-Robot Collaboration
2017-02-16Leveraging Union of Subspace Structure to Improve Constrained Clustering
2017-02-16Power of Active Sampling for Unsupervised Learning
2017-02-15Interactive Learning of Parsers from Weak Supervision
2017-02-15Robot Learning, Interaction and Reliable Autonomy
2017-02-15Does Randomness Solve Problems?
2017-02-15Robots Learning from Human Interactions
2017-02-15Sample-Efficient Reinforcement Learning with Rich Observations
2017-02-15Robot Learning from Motor-Impaired Teachers and Task Partners
2017-02-14Interactive Language Learning from the Extremes
2017-02-14Active Learning for Multidimensional Experimental Spaces of Biological Responses
2017-02-14Active Learning Beyond Label Feedback
2017-02-14Crowdsourcing and Machine Learning
2017-02-14Interactive Clustering
2017-02-13Stochastic Variance Reduction Methods for Policy Evaluation
2017-02-13Words, Pictures, and Common Sense
2017-02-13Interactively Learning Robot Objective Functions
2017-02-13Machine Teaching in Interactive Learning


Tags:
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Interactive Learning
Alekh Agarwal