Lex Fridman Podcast
#434 – Aravind Srinivas: Perplexity CEO on Future of AI, Search & the Internet
Aravind Srinivas
A Berkeley professor, Aliosha Afros, has written some papers on this where in RL, what happens if you just don't have any reward signal? An agent just explores based on prediction errors. He showed that you can even complete a whole Mario game or a level by literally just being curious. because games are designed that way by the designer to keep leading you to new things.
0
💬
0
Comments
Log in to comment.
There are no comments yet.