Applying RL methods to gridworld. A series of stepping stones scripts to capture the essence of RL
grid_test_env.py Introduces the grid world environment created by the good folks at MILA (Montreal Canada) .
grid_random_movement.py Introduces the concept of actions that are random. There is no learning and the high rewards are by chance. Press any key to start the random actions sequence
/basics Vanilla implementation of grid world for Value and Policy Iteration
/gym Using gym frozen world to implement RL algorithms