Place desired file in the src folder.
Our program takes 4 arguments
qlearning [The name of the file to read in representing the map ] [How long to learn (in seconds)] [The probability of moving in the desired direction upon taking an action] [The constant reward for each action]
Our program outputs the solution by displaying the optimal state to navigate to from each state.
We would like to attribute credit to Github user technobium for the Q-Learning algorithm base implementation that we utilized. We used this as the basis for our repository from which we modified to fulfill the expectations of the assignment. REPO