Real-time strategy video games have proven to be a very challenging area for applications of artificial intelligence research. With their vast state and action spaces and real-time constraints, existing AI solutions have been shown to be too slow, or only able to be applied to small problem sets, while human players still dominate RTS AI systems. This paper makes three contributions to advancing the state of AI for popular commercial RTS game combat, which can consist of battles of dozens of units. First, we present an efficient system for modelling abstract RTS combat called SparCraft, which can perform millions of unit actions per second and visualize them. We then present a modification of the UCT algorithm capable of performing search in games with simultaneous and durative actions. Finally, a novel greedy search algorithm called Portfolio Greedy Search is presented which uses hill climbing and accurate playout-based evaluations to efficiently search even the largest combat scenarios. We demonstrate that Portfolio Greedy Search outperforms state of the art Alpha-Beta and UCT search methods for large StarCraft combat scenarios of up to 50 vs. 50 units under real-time search constraints of 40 ms per search episode.
[1]
Michael Buro,et al.
Fast Heuristic Search for RTS Game Combat Scenarios
,
2012,
AIIDE.
[2]
Santiago Ontañón,et al.
Kiting in RTS Games Using Influence Maps
,
2012,
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.
[3]
Manfred K. Warmuth,et al.
Finding a Shortest Solution for the N × N Extension of the 15-PUZZLE Is Intractable
,
1986,
AAAI.
[4]
Alan Fern,et al.
UCT for Tactical Assault Planning in Real-Time Strategy Games
,
2009,
IJCAI.
[5]
Michael Buro,et al.
Heuristic Search Applied to Abstract Combat Games
,
2005,
Canadian Conference on AI.
[6]
Michael Buro,et al.
On the Complexity of Two-Player Attrition Games Played on Graphs
,
2010,
AIIDE.