Note: The Phase 6 milestones page is the existing phase-3 URL in this repo (naming predates the 0–8 phase list). This module links there for milestones and the Gridworld-style project.
Phase 6
Phase 6 — RL foundations (tabular)
Volumes 1–2: MDPs, dynamic programming, Monte Carlo, TD, SARSA, and tabular Q-learning. Core theory before function approximation.
Module progress