Introducing hierarchical adversarial search, a scalable search procedure for real-time strategy games
作者： Michael Buro , Nicolas A. Barriga , Marius Stanescu
DOI: 10.3233/978-1-61499-419-0-1099
关键词: Adversarial system 、 State (computer science) 、 Hierarchy 、 Implementation 、 Action (philosophy) 、 Scalability 、 Abstraction (linguistics) 、 Artificial intelligence 、 Real-time strategy 、 Computer science
摘要: Real-Time Strategy (RTS) video games have proven to be a very challenging application area for Artificial Intelligence research. Existing AI solutions are limited by vast state and action spaces real-time constraints. Most implementations efficiently tackle various tactical or strategic sub-problems, but there is no single algorithm fast enough successfully applied full RTS games. This paper introduces hierarchical adversarial search framework which implements different abstraction at each level — from deciding how win the game top of hierarchy individual unit orders bottom.
skatgame.net 参考文章(9)
John E. Laird, Joseph Xu, Sam Wintermute, SORTS: a human-level approach to real-time strategy AI national conference on artificial intelligence. pp. 55- 60 ,(2007)
Michael Buro, Call for AI Research in RTS Games ,(2004)
Michael Buro, Michael Chung, Jonathan Schaeffer, Monte Carlo Planning in RTS Games. computational intelligence and games. ,(2005)
Gabriel Synnaeve, Pierre Bessiere, Special tactics: A Bayesian approach to tactical decision-making computational intelligence and games. pp. 409- 416 ,(2012) , 10.1109/CIG.2012.6374184
David Churchill, Michael Buro, Portfolio greedy search and simulation for large-scale combat in starcraft computational intelligence and games. pp. 1- 8 ,(2013) , 10.1109/CIG.2013.6633643
Santiago Ontanon, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David Churchill, Mike Preuss, A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft IEEE Transactions on Computational Intelligence and AI in Games. ,vol. 5, pp. 293- 311 ,(2013) , 10.1109/TCIAIG.2013.2286295
Michael Buro, David Churchill, Build order optimization in StarCraft national conference on artificial intelligence. pp. 14- 19 ,(2011)
Santiago Ontañón, The Combinatorial Multi-armed Bandit problem and its application to real-time strategy games national conference on artificial intelligence. pp. 58- 64 ,(2013)
Frantisek Sailer, Michael Buro, Marc Lanctot, Adversarial Planning Through Strategy Simulation computational intelligence and games. pp. 80- 87 ,(2007) , 10.1109/CIG.2007.368082