One-Minute Research: Han Wang

We issued a challenge to students contributing to this year's International Conference on Learning Representation: explain their work in one minute.
Han Wang is a PhD student at the University of Alberta, who is supervised by Amii Fellows & Canada CIFAR AI Chairs Adam White and Martha White. She gives a technical breakdown of "Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay." Check out the full paper here: openreview.net...

[@Shaheen-c1g]

It is definitely better than first time . 😄