How DeepSeek R1's Reinforcement Learning Works Through GRPO

How DeepSeek R1's Reinforcement Learning Works Through GRPO

Oxen via YouTube Direct link

31:09 Training a Rust Reasoner

9 of 9
Previous

9 of 9

31:09 Training a Rust Reasoner

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

How DeepSeek R1's Reinforcement Learning Works Through GRPO

Automatically move to the next video in the Classroom when playback concludes
  1. 1 0:00 Intro
  2. 2 0:52 Recap of R1
  3. 3 2:35 Why is GRPO Important
  4. 4 3:41 From PPO to GRPO
  5. 5 7:31 Reducing Memory Usage with GRPO
  6. 6 12:23 Group Relatives Advantages
  7. 7 20:41 KL-Divergence
  8. 8 27:53 The Reward Signals
  9. 9 31:09 Training a Rust Reasoner

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.