Lecture 22 - From REINFORCE to GRPO
Presented by Joseph E. Gonzalez
- Recording
- Slides (PDF, pptx)
- Code (HTML, Colab, GitHub)
- Reading: Sections 13.4 and 13.5 (REINFORCE with baseline, actor-critic) of Sutton and Barto, Reinforcement Learning: An Introduction; Lecture 6 of CS 185/285: Deep Reinforcement Learning (Levine); Schulman et al., 2017 (PPO); Shao et al., 2024 (GRPO)