Run the main.py to train and test the Qtable

The environment is a 5x5 maze which contain walls in between. The agent starts at the top left corner(State 0 or Position [0,0]). The final goal is to reach the end of the maze, which is at the bottom left corner (State 24 or position [4,4]). The walls of the maze can be configured by passing the state values as inputs to the constructor.