Using influence maps with heuristic search to craft sneak-attacks in Starcraft

Abstract

Real-Time Strategy (RTS) games have consistently been popular among AI researchers over the past couple of decades due to their complexity and difficulty to play for both humans and AI. A popular strategy in RTS games is a “Sneak-Attack,” where one player tries to maneuver some of their units into the base of their enemy without being seen for as long as possible to surprise their enemy and deal massive damage to their economy. This thesis introduces a novel method for finding Sneak-Attack paths in StarCraft: Brood War by combining influence maps with heuristic search. The combined system creates paths that can guide units effectively - and automatically - into the enemy’s base, by avoiding enemy unit vision and minimizing both travel distance and unit damage. For StarCraft, this involves guiding a loaded transport ship to the enemy’s base to drop off units for attack. Our results show that the new system performs better than direct paths across a variety of maps in terms of total transport deaths, total damage taken, as well as the total time spent by the transport within enemy vision. We then utilize this new system to demonstrate an alternate use: a proof of concept for calculating building placements to defend against enemy sneak-attacks.