This is a repository for implementing RL basic code from David Silver's https://www.davidsilver.uk/teaching/

1. GLIE Monte Carlo Control
2. SARSA
3. n-step SARSA
4. backward SARSA
5. Q-Learning

1. GLIE Monte Carlo Control Value Function Approximation
2. SARSA Value Function Approximation
3. n-step SARSA Value Function Approximation
4. backward SARSA Value Function Approximation
5. Q-Learning Value Function Approximation

1. Monte Carlo Control Policy
2. Action Value Actor Critic

Plot maze with Dyna-Q Algorithm

8ILP_cute.py : maze with cute ver

8ILP_color.py : maze with color ver