Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
paradite
9 months ago
|
parent
|
context
|
favorite
| on:
Google is winning on every AI front
I forgot to mention that OpenAI also invented PPO, which is the default algorithm that everyone uses for RL since 2017:
https://en.wikipedia.org/wiki/Proximal_policy_optimization
DeepSeek's GRPO is also just a minor variant of PPO.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
DeepSeek's GRPO is also just a minor variant of PPO.