HackerTrans
トップ新着トレンドコメント過去質問紹介求人

monadicmonad

no profile record

投稿

Experimenting with policy gradient methods in Jax

github.com
2 ポイント·投稿者 monadicmonad·昨年·0 コメント

Policy Evaluation in Grid World

github.com
1 ポイント·投稿者 monadicmonad·2 年前·0 コメント

コメント

monadicmonad
·4 か月前·議論
why do I want them in a single system?
monadicmonad
·5 か月前·議論
its because benchmarks are nonsense and when you actually use OI models for programming they suck
monadicmonad
·昨年·議論
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 年前·議論
[dead]
monadicmonad
·3 年前·議論
I can 100% taste the plastic in any bottled water.