💡 Phase 2 — Value-Based Methods

Learn how to estimate optimal action-value functions.

Topics

• ε-Greedy Exploration
• SARSA (On-Policy TD Control)
• Q-Learning (Off-Policy TD Control)
• Experience Replay
• Function Approximation (Linear / Neural Networks)

Mini Projects

• FrozenLake-v1 (Tabular Q-Learning)
• CartPole-v1 (Neural Q-Learning)

📁 Source folder:
02-Value-Based