I'm trying to solve Rubik's cube using deep learning and I came across with DQN, so I decided to give it a try. I developed all the code and started training but I got this results: enter image description here

Loss goes up and test never get better results. I have tried to change learning rate, epsilon greedy decay, reducing scramble moves to one but it still can't solve it with just one move. That's why I would like to know if it just impossible to do it this way or I could miscalculating some values.

  • $\begingroup$ Is the question theoretical - "is it possible?" or practical - "how to do it"? $\endgroup$ Jun 4, 2021 at 13:51

1 Answer 1


I think yes, you can, since rubric group can be represented as a grid word environment.

See this link from GitHub, they attempted solving using dqn


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.