wr
hn
Top
New
Best
Ask
Show
Jobs
Back
m
monadicmonad
Joined 2 years ago
Karma
-1
Submissions
9
Member since
Jan 10
View on Hacker News
Recent submissions
Comment · 3 months ago
super duper serious
Comment · 8 months ago
why do I want them in a single system?
Comment · 8 months ago
its because benchmarks are nonsense and when you actually use OI models for programming they suck
Experimenting with policy gradient methods in Jax
g
github.com
2
monadicmonad
1 year ago
0
comments
Comment · 1 year ago
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.
Policy Evaluation in Grid World
g
github.com
1
monadicmonad
1 year ago
0
comments
Comment · 2 years ago
I can 100% taste the plastic in any bottled water.