Filters








1 Hit in 5.8 sec

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

Dylan Ashley, Anssi Kanervisto, Brendan Bennett
2021 arXiv   pre-print
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.  ...  2 according to several random people we asked, this is shown by one of the following works: , Neal and , Fahlman et al. [1983] , Guan et al. [2018] , Hinton [2000] , McDermott and Hinton [1986] ,  ... 
arXiv:2104.00698v1 fatcat:kolmfhs7hbbpbdikjfao4k4eym