A Rubik’s cube is a 3D puzzle that has 6 faces, each face usually has 9 stickers in a 3x3 layout and the objective of the
puzzle is to achieve the solved state where each face only has a unique color.
The possible states of a 3x3x3 Rubik’s cube are of the order of the quintillion and only one of them is considered the “solved”
state. This means that the input space of any Reinforcement Learning agent trying to solve the cube is huuuuuge.
The puzzle consists of twenty-six unique miniature cubes, also called "cubies" or "cubelets". Each of these includes a concealed inward extension that interlocks with the other cubes while permitting them to move to
different locations. The Cube can be taken apart without much difficulty, typically by rotating the top layer by 45° and then prying one of its edge cubes away from the other two layers. Consequently, it is a simple process to
"solve" a Cube by taking it apart and reassembling it in a solved state