Python implementations of all programming exercises in Sutton and Barto's book Reinforcement Learning: An Introduction (2nd Edition). Code for each exercise is contained in its own folder along with a readme detailing the solution and its conclusions. The code is written to provide a short and simple solution and often does not reflect standard RL conventions.
To view the solution for an exercise simply navigate to the respective folder. The code for each exercise is in a self-contained python file and can be easily run with the command:
python exercise-number.py