Several different controller representations are compared on anon-trivial problem in simulated car racing, with respect tolearning speed and final fitness. The controller representations arebased either on Neural Networks or Genetic Programming, and alsodiffer in regards to whether they allow for stateful controllers orjust reactive ones. Evolved GP trees are analysed, and attempts aremade at explaining the performance differences observed. Read more...

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 trains a team of agents through a series of customized exercises. To demonstrate this concept, the Neuroevolving Robotic Operatives (NERO) game was built based on rtNEAT. In NERO, the player trains a team of virtual robots for combat against other players' teams. 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 through interactive and adapting games. Read more...

In a time-to-market environment, designers may not be able to incorporate all the design features in a computer game. For each feature, there are several levels of implementation, which is corresponded to different levels of benefit as well as cost. Therefore, a trade-off decision for determining appropriate levels of implementation is very important, yet has been rarely studied in literature. This paper presents an approach to solve the trade-off decision problem. This approach applies the neural network technique and develops a genetic algorithm to optimize the design of computer games. By this approach, a near-optimal design alternative can be identified in a timely fashion. Read more...