The NERO Real-time Video Game (2004)
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 as the game is played, 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 an entirely 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 NeuroEvolving Robotic Operatives (NERO) game, the player trains a team of robots for combat. This paper describes results from this novel application of machine learning, and demonstrates that rtNEAT makes possible video games like NERO where agents evolve and adapt in real time. In the future, rtNEAT may allow new kinds of educational and training applications.
Technical Report AI-TR-04-312, Department of Computer Sciences, The University of Texas at Austin, Austin, TX, October 2004.

Bobby D. Bryant Ph.D. Alumni bdbryant [at] cse unr edu
Risto Miikkulainen Faculty risto [at] cs utexas edu
Kenneth Stanley Postdoctoral Alumni kstanley [at] cs ucf edu