Designing competitive bots for a real time strategy game using genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8010

@InProceedings{DBLP:conf/cosecivi/Fernandez-AresGMCG14,

• author = "Antonio Fernandez-Ares and Pablo Garcia-Sanchez and Antonio Miguel Mora and Pedro A. Castillo and Juan Julian Merelo Guervos",
• title = "Designing competitive bots for a real time strategy game using genetic programming",
• booktitle = "Proceedings 1st Congreso de la Sociedad Espanola para las Ciencias del Videojuego, CoSECivi 2014",
• year = "2014",
• editor = "David Camacho and Marco Antonio Gomez-Martin and Pedro Antonio Gonzalez-Calero",
• series = "CEUR Workshop Proceedings",
• volume = "1196",
• pages = "159--172",
• address = "Barcelona, Spain",
• month = jun # " 24",
• publisher = "CEUR-WS.org",
• keywords = "genetic algorithms, genetic programming",
• bibsource = "dblp computer science bibliography, http://dblp.org",
• URL = "http://ceur-ws.org/Vol-1196",
• URL = "http://ceur-ws.org/Vol-1196/cosecivi14_submission_24.pdf",
• size = "14 pages",
• abstract = "The design of the Artificial Intelligence (AI) engine for an autonomous agent (bot) in a game is always a difficult task mainly done by an expert human player, who has to transform his/her knowledge into a behavioural engine. This paper presents an approach for conducting this task by means of Genetic Programming (GP) application. This algorithm is applied to design decision trees to be used as bot's AI in 1 vs 1 battles inside the RTS game Planet Wars. Using this method it is possible to create rule-based systems defining decisions and actions, in an automatic way, completely different from a human designer doing them from scratch. These rules will be optimised along the algorithm run, considering the bots' performance during evaluation matches. As GP can generate and evolve behavioural rules not taken into account by an expert, the obtained bots could perform better than human-defined ones. Due to the difficulties when applying Computational Intelligence techniques in the videogames scope, such as noise factor in the evaluation functions, three different fitness approaches have been implemented and tested in this work. Two of them try to minimise this factor by considering additional dynamic information about the evaluation matches, rather than just the final result (the winner), as the other function does. In order to prove them, the best obtained agents have been compared with a previous bot, created by an expert player (from scratch) and then optimised by means of Genetic Algorithms. The experiments show that the three used fitness functions generate bots that outperform the optimised human-defined one, being the area-based fitness function the one that produces better results.",

}

Genetic Programming entries for Antonio Fernandez-Ares Pablo Garcia-Sanchez Antonio M Mora Garcia Pedro A Castillo Valdivieso Juan Julian Merelo

Citations