Experimenting with policy gradient methods in Jaxgithub.com2 points·by monadicmonad·letztes Jahr·0 comments
monadicmonad·vor 5 Monaten·discussits because benchmarks are nonsense and when you actually use OI models for programming they suck
monadicmonad·letztes Jahr·discussI don't know how to go from understanding this material to having a job in the field. Just stuck as a SWE for now.