Collective Intelligence Community Podcast cover image

OpenPipe Co-Founder on Reinforcement Learning - David Corbitt | Ep. 22

Collective Intelligence Community Podcast

00:00

PPO, DPO, GRPO: When to Use Each

David summarizes PPO, DPO, and GRPO algorithms and their strengths for independent rewards, preference pairs, and grouped comparisons.

Play episode from 19:50
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app