Using Monte Carlo Tree Search in Soccer Kids

Implementing AI for turn-based tactical games is challenging, especially when the AI opponent must make decisions akin to a human player and provide a challenge in a one-on-one match. Moreover, if you add geometric considerations like planning for movement of physical objects, you get a recipe for an AI programmer’s headache. However, with the right tools, nothing is impossible! This chapter is a case study on AI bots developed for a unique tactical sports game, Soccer Kids by Acid Wizard. It describes a creative approach to Monte Carlo Tree Search, enhanced with clever space sampling techniques, custom state evaluation functions, and other useful tricks.