Implementation of the Easy21 assignment from the UCL course "Reinforcement Learning" by David Silver.

To run the code, simply execute the following command:

# mc control
python control/monte_carlo_control.py

# sarsa lambda control
python control/sarsa_lambda_control.py

# q learning control
python control/q_learning_control.py

# linear function approximation control
python control/sarsa_lambda_control_fa.py

Solution to #2: Monte Carlo Control in Easy21

Solution to #3: Sarsa(λ) in Easy21

Extension of #3: Q-learning in Easy21

Solution to #4: Linear Function Approximation in Easy21