← Back to curriculum
Phase 09 · 12 lessons
Reinforcement Learning
The foundation of RLHF and game-playing AI.
01MDPs, States, Actions & RewardsLearn02Dynamic Programming — Policy Iteration & Value IterationBuild03Monte Carlo Methods — Learning from Complete EpisodesBuild04Temporal Difference — Q-Learning & SARSABuild05Deep Q-Networks (DQN)Build06Policy Gradient — REINFORCE from ScratchBuild07Actor-Critic — A2C and A3CBuild08Proximal Policy Optimization (PPO)Build09Reward Modeling & RLHFBuild10Multi-Agent RLBuild11Sim-to-Real TransferBuild12RL for Games — AlphaZero, MuZero, and the LLM-Reasoning EraBuild