Evolutionary algorithms applied to learning in real time strategy games

• Grant number: 12/00995-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2012
• End date: April 30, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Claudio Fabiano Motta Toledo
• Grantee: Rodrigo de Freitas Pereira
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The present proposed scientific initiation project aims to apply Evolutionary Algorithms (EA) in real-time strategy games. This type of game is also known as Real-Time Strategy (RTS). The elaboration of strategies in these games is focused on the management of available resources and attack actions over the opponents. Thus, the decision must be taken considering when and what the better action to be executed. The evolutionary algorithms proposed will have their performance evaluated against real players, against default strategies within the game, and against at least one method from the literature that will be previously selected and implemented. An RTS game with open code is used as an environment for methods development and evaluation. The results will be reported in articles and submitted to congress within the game área.(AU)