• Prediction and Control with Function Approximation (Coursera)

• Dynamic Programming (Sutton & Barto)

• Finite Markov Decision Processes (Sutton & Barto)

• Multi-armed Bandits (Sutton & Barto)

• Temperal Difference Learning (Sutton & Barto)

• Monte Carlo Methods (Sutton & Barto)

• The Last Marble

• Policy Improvement Theorem (Sutton & Barto)

• Importance Sampling in Off-Policy Reinforcement Learning Algorithms