Game AI Pro 3

25

Combat Outcome Prediction for Real-Time Strategy Games

Marius Stanescu, Nicolas A. Barriga, and Michael Buro

25.1    Introduction

25.2    The Engagement Decision

25.3    Lanchester’s Attrition Models

25.4    Lanchester Model Parameters

25.5    Experiments

25.6    Conclusions

References

25.1  Introduction

Smart decision-making at the tactical level is important for AI agents to perform well in real-time strategy (RTS) games, in which winning battles is crucial. Although human players can decide when and how to attack based on their experience, it is challenging for AI agents to estimate combat outcomes accurately. Prediction by running simulations is a popular method, but it uses significant computational resources and needs explicit opponent ...