Skip to content
All tags

#policy-gradient

2 posts
ai deep-dive Reading Stanford CS229

Policy Gradient and Its Variants: REINFORCE and PPO

Chapter 21 derives REINFORCE with the log-derivative trick, then uses reward-to-go, baselines, and PPO clipping to control policy-gradient variance and update size.

#cs229#policy-gradient#reinforce#ppo#reinforcement-learning
learning guide Reading Berkeley CS285 Spring 2026

Berkeley CS285 L5–10: Policy Gradients, Actor-Critic, DQN, and SAC

L5–10 build the deep-RL core through policy- and value-based routes; HW2 is CPU-friendly, while HW3's Atari and HalfCheetah runs can require hours of GPU time.

#cs285#berkeley#policy-gradient#q-learning#actor-critic