unreviewed draftNo one has checked this end to end. Treat the math, code, and citations as unverified. Source on GitHub.
Topic: Q-learning, DQN, target networks. Goes with: lecture L03. Status: planned. To be built next.
The plan: derive the Q-learning update from the Bellman optimality equation; explain why DQN needs a target network and replay buffer; implement tabular Q (links to exercises/03-q-learning/) and outline DQN.