In this paper, we explore and compare multiple algorithms for solving the\ncomplex strategy game of Terra Mystica, hereafter abbreviated as TM. Previous\nwork in the area of super-human game-play using AI has proven effective, with\nrecent break-through for generic algorithms in games such as Go, Chess, and\nShogi \\cite{AlphaZero}. We directly apply these breakthroughs to a novel\nstate-representation of TM with the goal of creating an AI that will rival\nhuman players. Specifically, we present the initial results of applying\nAlphaZero to this state-representation and analyze the strategies developed. A\nbrief analysis is presented. We call this modified algorithm with our novel\nstate-representation AlphaTM. In the end, we discuss the success and\nshortcomings of this method by comparing against multiple baselines and typical\nhuman scores. All code used for this paper is available at on\n\\href{https://github.com/kandluis/terrazero}{GitHub}.\n