Predicting the Outcome of Small Battles in StarCraft
Antonio A. S · 2015
Real-Time Strategy (RTS) games are popular testbeds for AI researchers. In this paper we compare dierent machine learning al- gorithms to predict the outcome of small battles of marines in StarCraft, a popular RTS game. The predictions are made from the perspective of an external observer of the game and they are based only on the actions that the dierent units perform in the battleeld. Our empirical results show that case-based approaches based on k-Nearest Neighbor classica- tion outperform other standard classication