Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
Implementing DeepSeek R1's GRPO algorithm from scratch
(
github.com/policy-gradient
)
192 points
by
xcodevn
3 months ago
|
past
|
3 comments
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
