Experimenting with policy gradient methods in Jaxgithub.com2 points·by monadicmonad·vorig jaar·0 comments
monadicmonad·5 maanden geleden·discussits because benchmarks are nonsense and when you actually use OI models for programming they suck
monadicmonad·vorig jaar·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.