Combining Expert Knowledge and Learning from Demonstration in Real-Time Strategy Games
Case-based planning (CBP) is usually considered a good solution to solve the knowledge acquisition problem that arises when developing AIs for real-time strategy games. Unlike more classical approaches, such as state machines or rule-based systems, CBP allows experts to train AIs directly from games recorded by expert players. Unfortunately, this simple approach has also some drawbacks, for example it is not easy to refine an existing case base to learn specific strategies when a long game session is needed to create a new trace. Furthermore, CBP may be too reactive to small changes in the game state and, at the same time, do not respond fast enough to important changes in the opponent’s strategy. We propose to alleviate these problems by letting experts to inject decision making knowledge into the system in the form of behavior trees, and we show promising results in some experiments using Starcraft.
KeywordsGame Designer Behavior Tree Domain Theory Query Node Primitive Action
Unable to display preview. Download preview PDF.
- 1.AIIDE: StarCraft AI competition. As Part of the Program of the Artificial Intelligence and Interactive Digital Entertainment Conference (2010)Google Scholar
- 2.Blizzard: Starcraft game (1998), http://us.blizzard.com/en-us/games/sc
- 3.Flórez-Puga, G., Llansó, D., Gómez-Martín, M.A., Gómez-Martín, P.P., Díaz-Agudo, B., González-Calero, P.A.: Empowering Designers with Libraries of Self-validated Query-enabled Behaviour Trees. In: Artificial Intelligence for Computer Games, pp. 55–82. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 4.Isla, D.: Halo 3 - building a better battle. In: Game Developers Conference (2008)Google Scholar
- 5.Krajewski, J.: Creating all humans: A data-driven AI framework for open game worlds. Gamasutra (February 2009)Google Scholar
- 8.Millington, I., Funge, J.: Artificial Intelligence for Games, 2nd edn. Morgan Kaufmann, San Francisco (2009)Google Scholar
- 9.Muñoz-Avila, H., Aha, D.W., Nau, D.S., Weber, R., Breslow, L., Yamal, F.: Sin: integrating case-based reasoning with task decomposition. In: IJCAI 2001: Proceedings of the 17th International Joint Conference on Artificial Intelligence, pp. 999–1004 (2001)Google Scholar
- 10.Ontañón, S., Bonnette, K., Mahindrakar, P., Gómez-Martín, M.A., Long, K., Radhakrishnan, J., Shah, R., Ram, A.: Learning from human demonstrations for real-time case-based planning. In: Kuter, U., Muñoz-Avila, H. (eds.) Proceedings of the IJCAI 2009 Workshop on Learning Structural Knowledge From Observations (2009), http://www.cs.umd.edu/~ukuter/struck09/index.html
- 11.Ontañón, S., Mishra, K., Sugandh, N., Ram, A.: On-line case-based planning. Computational Intelligence 26(1), 84–119 (2010), http://dx.doi.org/10.1111/j.1467-8640.2009.00344.x MathSciNetCrossRefGoogle Scholar
- 12.Palma, R., González-Calero, P.A., Gómez-Martín, M.A., Gómez-Martín, P.P.: Extending case-based planning with behavior trees. In: 24th Florida Artificial Intelligence Research Society Conference (to appear, 2011)Google Scholar
- 14.Weber, B.: Integrating expert knowledge and experience. In: AAAI Doctoral Consortium (2010)Google Scholar