Welcome to the second installment of my attempt to solve a Rubik’s Cube via reinforcement learning (RL). Last time, I provided an intro to Markov Decision Processes (MDPs) and formulated the task of solving a Rubik’s Cube as an MDP. If you missed this post or would like a quick refresher, you can check it out here.

At the end of my last post, I left off with a discussion of the Q-function and how we will need to approximate it for our task since the space of state-action pairs is too large. In this post, I will implement a neural network to do exactly that. Along the way, we will explore how the network is trained via the Experience Replay algorithm and provide some initial experimental results. In case you are curious, my actual Python implementation is here. As always, any comments, questions, or feedback is much appreciated!

#deep-q-learning #rubiks-cube #personal-project #machine-learning