GHOST: A Combinatorial Optimization Solver for RTS-related Problems

Florian Richoux (1) , Alberto Uriarte (2) , Jean-François Baffier (3)

1 TASC - Theory, Algorithms and Systems for Constraints
2 Drexel University
3 UTokyo - The University of Tokyo

This paper presents GHOST, a combinatorial optimization solver an RTS AI developer can use as a blackbox to solve any problems encoded by a constraint satisfaction/optimization problem. We show a way to model three very different RTS problems by a constraint satisfaction/optimization problem, each problem belonging to a specific level of abstraction, and test our solver on them, using StarCraft as a testbed. For the three problems (the target selection problem, the wall-ion problem and the build order planning problem), GHOST shows very good results computed within some tens of milliseconds. Game AI,

Mots clés: COP; Combinatorics; Optimization; Solver; StarCraft; CSP; Real-Time Strategy; Game AI

Domaines: Intelligence artificielle [cs.AI]

Florian Richoux, Alberto Uriarte, Jean-François Baffier. GHOST: A Combinatorial Optimization Solver for RTS-related Problems. IEEE Transactions on Computational Intelligence and AI in games, 2016, ⟨10.1109/TCIAIG.2016.2573199⟩. ⟨hal-01152231v2⟩