How It Works
Structure
The cleanest pieces are the REINFORCE notebooks and the actor-critic transcripts. Around that, you have several Pong PPO/REINFORCE experiments, support utilities, and saved policy checkpoints.
REINFORCE + PPO + Actor-Critic theory
Policy gradients and actor-critic studies
The theory-heavy branch that ties together REINFORCE, PPO, A2C/A3C, GAE, and your Pong experiments.
Strong archive; selective live reuse
Legacy Atari stack for some assets
Why Reuse
Role in the new DRL arm
This is the best source for explanatory pages about variance reduction, baselines, clipped objectives, and the move from vanilla policy gradients into actor-critic methods.
Key Assets
What is already here
REINFORCE
notebook setCartPole notebook pair plus additional exploratory notebooks.
source-material/reinforce
Pong PPO / REINFORCE
experiment branchMultiple notebooks, vectorized env utilities, and saved `.policy` checkpoints.
source-material/reinforce/pong-PPO-REINFORCE
Actor-Critic Transcripts
subtitle archiveA2C, A3C, GAE, DDPG, and related lecture transcripts.
source-material/classwork/ContinuousControl_Transcripts
A2C / PPO / GAE Papers
paper setReference PDFs for A2C/A3C, PPO, GAE, and TRPO-style ideas.
resources