🎯 Phase 1 — RL Fundamentals

Master the core mathematical and algorithmic foundations of Reinforcement Learning.

Topics

• Agent–Environment Interaction
  → Explore Agent–Environment Interaction ▸
• Markov Decision Processes (MDPs)
  → Explore Markov Decision Processes ▸
• Bellman Expectation & Optimality Equations
  → Explore Bellman Equations ▸
• Dynamic Programming
  → Start with Policy Evaluation ▸
  → Continue with Policy Iteration ▸
  → Explore Value Iteration ▸
• Monte Carlo Methods
  → Explore Monte Carlo ▸
• Temporal-Difference (TD) Learning
  → Explore TD Learning ▸

Mini Projects

• Gambler’s Problem (DP + Value Iteration)
  → Check here: Gambler’s Problem Project ▸
• Blackjack — Monte Carlo Control
  → Try it here: Blackjack Project ▸
• Random Walk — TD(0) Learning Curve
  → Explore here: Random Walk Project ▸
• FrozenLake — Monte Carlo vs TD Comparison
  → Check here: FrozenLake Project ▸

📁 Source folder:
01-Fundamentals