6: Deep Reinforcement Learning at the Edge of the Statistical Precipice from Argmax

Argmax

Vahe Hagopian, Taka Hasegawa, Farrukh Rahman

6: Deep Reinforcement Learning at the Edge of the Statistical Precipice

1 hour 1 minutes Posted Jun 6, 2022 at 11:00 pm.

0:00

1:01:08

Share at current time

Show notes

We discuss NeurIPS outstanding paper award winning paper, talking about important topics surrounding metrics and reproducibility.