Experimenting with policy gradient methods in Jaxgithub.com2 points·by monadicmonad·l’année dernière·0 comments
monadicmonad·il y a 5 mois·discussits because benchmarks are nonsense and when you actually use OI models for programming they suck
monadicmonad·l’année dernière·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.