In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet if game characters could learn through interacting with the player, behavior could improve during gameplay, keeping it interesting. This paper introduces the real-time NeuroEvolution of Augmenting Topologies (rtNEAT) method for evolving increasingly complex artificial neural networks in real time, as a game is being played. The rtNEAT method allows agents to change and improve during the game. In fact, rtNEAT makes possible a new genre of video games in which the player teaches a team of agents through a series of customized training exercises. In order to demonstrate this concept in the NeuroEvolvingRoboticOperatives (NERO) game, the player trains a team of robots for combat. This paper describes results from this novel application of machine learning, and also demonstrates how multiple agents can evolve and adapt in video games like NERO in real time using rtNEAT. In the future, rtNEAT may allow new kinds of educational and training applications that adapt online as the user gains new skills.
[ Winner of the CIG'05 Best Paper Award ]