Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search

TL;DR

This paper introduces AlphaChute, a deep neural network and tree search-based algorithm that achieves superhuman performance in Chutes and Ladders, converging to Nash equilibrium efficiently and with a straightforward implementation.

Contribution

It presents the first formal proof of convergence to Nash equilibrium in Chutes and Ladders using deep learning and tree search techniques.

Findings

AlphaChute surpasses human performance in Chutes and Ladders.

The algorithm converges to Nash equilibrium in constant time.

Implementation remains simple due to domain-specific adaptations.

Abstract

We present AlphaChute: a state-of-the-art algorithm that achieves superhuman performance in the ancient game of Chutes and Ladders. We prove that our algorithm converges to the Nash equilibrium in constant time, and therefore is -- to the best of our knowledge -- the first such formal solution to this game. Surprisingly, despite all this, our implementation of AlphaChute remains relatively straightforward due to domain-specific adaptations. We provide the source code for AlphaChute here in our Appendix.