Reinforcement Learning is a trial and error application of ML, in which everytime the
algorithm performs an action it gets rewarded. The overall obejective of the algorithm
is to maximize the reward. It remembers the previously taken actions through two very
important matrices: the R-Matrix and the Q-Matrix.
The R-Matrix maps the current state of the algorithm with the reward it will recibe for
taking a determined action. On the other hand, the Q-Matrix is the "memory" of the algorithm
and maps the rewards of the R-Matrix showing how to achieve the highest reward based on the
previous states.
In this implementation, we will use the graph shown below to find the shortest path between
two nodes. The user needs to enter both the initial and the final node.
