Sham Kakade

  1. Title:
    Policy Gradient Methods, Curvature, and Distribution Shift
    Speaker:
    Sham Kakade

    Link:
    https://video-archive.fields.utoronto.ca/view/12934

  2. Title:
    Tradeoffs in large scale learning: statistical accuracy vs. numerical precision
    Speaker:
    Sham Kakade

    Link:
    https://video-archive.fields.utoronto.ca/view/3278

  3. Title:
    Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning
    Speaker:
    Sham Kakade

    Link:
    https://www.ias.edu/video/NewDirections/2019/1108-ShamKakade

  4. Title:
    Reinforcement Learning, Deep Learning,
and the Role of Policy Gradient Methods
    Speaker:
    Sham Kakade

    Link:
    https://www.ias.edu/video/theorydeeplearning/2019/1018-ShamKakade