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.
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