Minesweeper Reinforcement Learning Explained

What is Minesweeper?
It is a game where you find a certain number of bombs on a board based on clues on the numbers on the board

This is the bomb you are finding
These flags indicate which tiles you think are bombs
Numbers indicate how many bombs are around that tile. In this example, there are 2 bombs around the middle tile and the rest are safe so 2 is shown.
Examples!
Where are the bombs? Try to solve them yourself then hover over for the answer!