The theory of Proximal Policy Optimisation implementations 2024-04-11T13:00:35.662Z

Comment by salman.mohammadi on An interactive introduction to grokking and mechanistic interpretability · 2023-08-13T23:04:48.810Z · LW · GW

This is a delightful exposition of grokking. I'm very glad to see such a beautiful phenomenom deserve a similarly striking visualisation.

What are you writing these visualisations in?