Week 4 enters ML: supervised classification (k-NN, SVM, Perceptron), model evaluation, RL basics (MDP, Q-learning, ε-greedy). Projects: Shopping (purchase prediction with k-NN) and Nim (learning to play via Q-learning).
Lecture 22 keeps the MDP structure but removes known transitions and rewards. TD learning updates value from one sample, and Q-learning uses an off-policy target to learn optimal action values directly.
Lectures 9–12 and Project 3 use the same Gridworld to contrast value iteration with a known model, Q-learning from unknown dynamics, and approximate Q-learning that generalizes through features.
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.
The third reason Go can't be learned with supervision is the interesting one: the ground truth itself is ill-defined — the strongest human doesn't play their best moves every day, and even their best move isn't optimal. The last 20 minutes map RLHF fully back onto RL: the agent is the model being fine-tuned, the action is the next token, an episode is one full generation, and the reward is extremely sparse.