Case Indexing Using PSO and ANN in Real Time Strategy Games

Authors:
Peng Huo;Simon Chi-Keung Shiu;Haibo Wang;Ben Niu
Affiliations:
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China;Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China;Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China;Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
Venue:
PReMI '09 Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence
Year:
2009

Citing 8
Cited 0

How Qualitative Spatial Reasoning Can Improve Strategy Game AIs

IEEE Intelligent Systems
Foundations of Soft Case-Based Reasoning

Foundations of Soft Case-Based Reasoning
AI for Game Developers

AI for Game Developers
Fundamentals of Computational Swarm Intelligence

Fundamentals of Computational Swarm Intelligence
Using genetically optimized artificial intelligence to improve gameplaying fun for strategical games

Sandbox '08 Proceedings of the 2008 ACM SIGGRAPH symposium on Video games
Comparison among five evolutionary-based optimization algorithms

Advanced Engineering Informatics
Application and Comparison of Particle Swarm Optimization and Genetic Algorithm in Strategy Defense Game

ICNC '09 Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 05
Playing to learn: case-injected genetic algorithms for learning to play computer games

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a case indexing method using particle swarm optimization (PSO) and artificial neural network (ANN) in a defense-style real time strategy (RTS) game. PSO is employed to optimize the placement of cannons to defend the enemy attack. The execution time of PSO ( 100 seconds) is unsatisfied for RTS game. The result of PSO is used as a case indexing of past experience to train ANN. After the training (approximately 30 seconds), ANN can obtain the best cannon placement within 0.05 second. Experimental results demonstrated that this case indexing method using PSO and ANN efficiently speeded up the whole process to satisfy the requirement in RTS game.