What I Read: How Generally Capable Agents Trained

https://www.lesswrong.com/posts/DreKBuMvK7fdESmSJ/how-deepmind-s-generally-capable-agents-were-trained

How DeepMind’s Generally Capable Agents Were Trained
by 1a3orn
20th Aug 2021

“One of DeepMind’s latest papers… explains how DeepMind produced agents that can successfully play games as complex as hide-and-seek or capture-the-flag without even having trained on or seen these games before. As far as I know, this is an entirely unprecedented level of generality for a reinforcement-learning agent.”