Reinforcement learning achieved significant results that received publication and influence, systems that were based on RL in a variety of games such as StarCraft, GO and poker(games that until recently were considered unsolvable due to it enormous number of states) reached results that surpass human performance.
The most two important elements of RL are Action and State, embedding the current state of a RL environment can help reduce the dimension of the possible states and by doing so save computation time and resources and memory as well, also, by encoding the states we can find similarities between states and choose the right action in a wiser way based in previous games.
The project of this goal was to build a NN to embed states of a game into a real numbers vector.