Amazing talk, describing the Antikythera Mechanism, a mechanical device from ancient Greece, 2200 years ago. via David Deutsch. https://www.youtube.com/watch?v=xWVA6TeUKYU&t=327s
Belated advertising for our NeurIPS 2022 paper. ReLU-based policies partition the input space into piecewise linear regions. How many regions are there? (Ans: related to # neurons; only weakly related to depth). Does the region density increase in areas that the policy learns to visit? (yes, moderately). See here for other lessons learned: https://www.cs.ubc.ca/~van/papers/2022-NeurIPS-understanding/index.html
For those who couldn't make it to CoRL 2022 (myself included), all the papers are available here: https://openreview.net/group?id=robot-learning.org/CoRL/2022/Conference
Just a quick reminder of the many interesting talks / interviews on the "Talk RL" podcast: https://www.talkrl.com/
Hello all! I'm interested in physics-based models of human movement, deep reinforcement learning, animation, and robotics. I'm a professor in the Dept of Computer Science at UBC, in Vancouver, Canada. List of recent projects can be found here:
I'm keen to stay connected to the research communities related to all the above areas!