Favorite tweets

We present ReQueST: a method for training RL agents from human feedback in the presence of unknown unsafe states. By @sidgreddy, @ancadianadragan, @svlevine, @ShaneLegg, @janleike
Paper: https://t.co/XD3Be6bX3t
Code: https://t.co/A0CkCBBmXe pic.twitter.com/qM8GSaMcr2

— DeepMind (@DeepMindAI) December 13, 2019

from Twitter https://twitter.com/DeepMindAI

December 13, 2019 at 05:57AM
via IFTTT