Master Reinforcement Learning
A daily quiz curriculum that builds intuition from Bellman equations to RLHF.
Curriculum
Week 1
The Bellman Contract
Week 2
Deep Q-Networks & Non-Stationarity
Week 3
Policy Gradients & The LLM Connection
Week 4
PPO — Build The Engine
Week 5
Reward Modeling & RLHF Theory
Week 6
DPO — The Closed-Form Revolution
Week 7
Reasoning RL — GRPO & R1-Style Training
Week 8
Capstone — Ship an Artifact
Active Recall
Retrieve concepts daily instead of passively re-reading.
Adaptive Progression
Pass a day to unlock the next. Missed topics are tagged for review.
Production Relevant
DQN to GRPO — the algorithms that power modern LLM training.