A Robust Approach to Noise for Plan Recognition in RTS Games

Trying to infer the strategy of the opponent is very important in games. Especially in Real-Time Strategy Games (RTS), where you have uncertainty and thus cannot see most of the opponent's actions, but you do not want to be unprepared for its strategy. Good human players can do it almost naturally, but it is a different story for AI players. Plan recognition is a challenging problem, especially with uncertainty and the number of possible actions and states of the world in RTS games. We address the problem of plan recognition in RTS games. We show that an approach based on plan recognition as planning and heuristic search can yield good results and be robust to noise. Furthermore, we found that such an approach has its accuracy decreasing slightly with noisy data, does not need any training beforehand, and could be easily adapted to different RTS games. Our approach allows us to infer in real-time the plan that a player might be pursuing in an RTS game, here we focus on the RTS game called StarCraft, but it could be adapted to many other RTS games.