Note: The Phase 7 milestones page uses URL phase-4 in this site. Deep RL theory lives in Volumes 3–5; the demo page is a UI sample, not a substitute for chapters.
Phase 7
Phase 7 — Deep RL
Volumes 3–5: value function approximation, DQN family, policy gradients, actor-critic, and advanced policy optimization (chapters 21–50).
Module progress