Videos

Start date cannot be after end date.
Integrating optimization, constraints, and control within deep learning models Thumbnail

Integrating optimization, constraints, and control within deep learning models

Presenter
  • Zico Kolter
February 26, 2020
IPAM
Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning Thumbnail

Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning

Presenter
  • Daniel Kuhn
February 26, 2020
IPAM
Safe and Efficient Exploration in Reinforcement Learning Thumbnail

Safe and Efficient Exploration in Reinforcement Learning

Presenter
  • Andreas Krause
February 26, 2020
IPAM
Learning Intended Costs: Extracting all the right information from all the right places Thumbnail

Learning Intended Costs: Extracting all the right information from all the right places

Presenter
  • Anca Dragan
February 25, 2020
IPAM
Curbing Our Enthusiasm: Constraining Decision Policies Learned from the Past to Ensure Good Futures Thumbnail

Curbing Our Enthusiasm: Constraining Decision Policies Learned from the Past to Ensure Good Futures

Presenter
  • Emma Brunskill
February 25, 2020
IPAM
Learning from Multiple Biased Sources Thumbnail

Learning from Multiple Biased Sources

Presenter
  • Clayton Scott
February 25, 2020
IAS
Trying to Make Sense of Control from Pixels Thumbnail

Trying to Make Sense of Control from Pixels

Presenter
  • Benjamin Recht
February 25, 2020
IPAM
Is the variety of singular tuples of matrices a null cone? Thumbnail

Is the variety of singular tuples of matrices a null cone?

Presenter
  • Viswambhara Makam
February 25, 2020
IAS
Learning Control from Minimal Prior Knowledge Thumbnail

Learning Control from Minimal Prior Knowledge

Presenter
  • Martin Riedmiller
February 25, 2020
IPAM
From pixels to torques: output feedback for robotics Thumbnail

From pixels to torques: output feedback for robotics

Presenter
  • Russell Tedrake
February 25, 2020
IPAM
"Observable events" and "typical trajectories" in finite and infinite dimensional dynamical systems Thumbnail

"Observable events" and "typical trajectories" in finite and infinite dimensional dynamical systems

Presenter
  • Lai-Sang Young
February 24, 2020
IAS
On the statistical complexity of reinforcement learning Thumbnail

On the statistical complexity of reinforcement learning

Presenter
  • Mengdi Wang
February 24, 2020
IPAM