A Computer-Games-Based AI Research Environment

To develop, test and experiment with new AI algorithms, researchers require an experimentation environment. This is even more necessary when we talk about developing agent and multiagent systems. Moreover, if doing performance comparisons of different algorithms is the goal, it is really important to put all those algorithms to work under the same environment conditions. At present, there is a great variety of environments developed to support AI researchers in their tasks. However, it is usual to find that these environments whether they have too specific aims or they perfom well just with some kind of algoritms. In addition, their tendence to be researcher-oriented prevent us from using them in other fields like education, diffusion or massive testing. In this paper we propose a new kind of multiagent research environment, based on a computer game called Screaming Racers, with which we try to surpass these difficulties. Our computer-games-based research environment is intended to be used simultaneously by researchers, students and general players, powering up research, education, diffusion and massive testing.