Consider the given scenario : Consider a robot that needs to learn how to leave a house in the best

path possible. We have a house with $5$ rooms, and one "exit" room. A graph representing it is given

below. On this graph all rooms are nodes, and the arrows the actions that can be taken on each

node. The arrow values are the immediate rewards that the agent receives by taking some action

on a specific room. We choose our reinforcement learning environment to give $0$ reward for all

rooms that are not the exit room. In our target room we give a $100$ reward. Let the discount factor

be $0\mathrm{.}7$ and the learning rate be $0\mathrm{.}4.$ An episode starts with a random start node and ends upon

reaching the target room.