Videos

Start date cannot be after end date.

A Lyapunov approach for finite-sample convergence bounds with off-policy RL

Presenter
  • Sanjay Shakkottai
August 3, 2021
ICERM

Batch Value Function Tournament

Presenter
  • Nan Jiang
August 3, 2021
ICERM

Planning and Learning from Interventions

Presenter
  • Caroline Uhler
August 3, 2021
ICERM

Preference based RL with finite time guarantees

Presenter
  • Aarti Singh
August 2, 2021
ICERM

Frank-Wolfe Methods in Probability Space

Presenter
  • Jose Blanchet
August 2, 2021
ICERM

Towards a Theory of Representation Learning for Reinforcement Learning

Presenter
  • Alekh Agarwal
August 2, 2021
ICERM

Reinforcement Learning in High Dimensional Systems (and why "reward" is not enough...)

Presenter
  • Sham Kakade
August 2, 2021
ICERM

A Boosting Approach to Reinforcement Learning

Presenter
  • Elad Hazan
August 2, 2021
ICERM
Quantum barren plateaus and a possible way out Thumbnail

Quantum barren plateaus and a possible way out

Presenter
  • Maria Kieferova
May 27, 2021
IMSI
From Speech AI to Finance AI and Back Thumbnail

From Speech AI to Finance AI and Back

Presenter
  • Li Deng
August 18, 2020
IAS
Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning Thumbnail

Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning

Presenter
  • Mikhail Belkin
April 21, 2020
IPAM
Margins, perceptrons, and deep networks Thumbnail

Margins, perceptrons, and deep networks

Presenter
  • Matus Telgarsky
March 26, 2020
IAS