Metaheuristics applied to the development of artificial intelligence for real time strategy games

• Grant number: 13/12522-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2013
• End date: February 28, 2014
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Claudio Fabiano Motta Toledo
• Grantee: Leonardo Tórtoro Pereira
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The proposed undergraduate research project aims to apply metaheuristics in Real-Time Strategy (RTS) games. In these games, strategies must be developed in order to attack opponents, but also considering the capture and management of available resources. The player must make decisions throughout the game from a scope of possible actions. This scope may vary according to the RTS game considered. Initially, the project will continue the studies begun in FAPESP 2012/00995-0, "Evolutionary Algorithms Applied to Learning in Real Time Strategy Games". New approaches by applying evolutionary algorithms from those presented in FAPESP 2012/00995-0 will be implemented. In addition, new methods based on other metaheuristics will be proposed. This project will also assess the methods in at least two RTS games with open source. The results will be presented through the preparation of articles that will be submitted to conferences and journals. (AU)