From REINFORCE to PPO/GRPO - Homepage
The home page of PG series.
#Machine Learning
5 posts
TRPO and PPO
From the KL-constrained update to TRPO and PPO's clipped surrogate objective.
Introduction to Reinforcement Learning
A brief introduction to RL.
Intro to REINFORCE
Introduction to REINFORCE algorithm.
On-policy and Off-policy
Introduction to complete on-policy and off-policy algorithms.