HackerTrans
TopNewTrendsCommentsPastAskShowJobs

monadicmonad

no profile record

Submissions

Experimenting with policy gradient methods in Jax

github.com
2 points·by monadicmonad·tahun lalu·0 comments

Policy Evaluation in Grid World

github.com
1 points·by monadicmonad·2 tahun yang lalu·0 comments

comments

monadicmonad
·4 bulan yang lalu·discuss
why do I want them in a single system?
monadicmonad
·5 bulan yang lalu·discuss
its because benchmarks are nonsense and when you actually use OI models for programming they suck
monadicmonad
·tahun lalu·discuss
I don't know how to go from understanding this material to having a job in the field. Just stuck as a SWE for now.
monadicmonad
·2 tahun yang lalu·discuss
[dead]