Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search. (arXiv:2104.00698v1 [cs.AI])

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.

Source: https://arxiv.org/abs/2104.00698

webmaster

Related post