Jeff Clune
TalkRL: The Reinforcement Learning Podcast
00:00
AIGA: A Paradigm for Automated Training Environments
I think a lot of the work that I have done in the past and that I'm currently doing is very much in this paradigm. So one of the, I think VPT for example is kind of an example of how you can use the fourth pillar to dramatically accelerate things. Ultimately if you wanted to generate a lot of really complicated training domains like Minecraft and using computers and driving a car, etc, etc, it might be very inefficient to have to bootstrap up and learn how to do that from scratch. But if you can learn from humans and how they play video games and how they drive and driving simulators and how they use their computers, then you might be able to catch right
Transcript
Play full episode
