Real-Time Neuroevolution in the NERO Video Game
Top Cited Papers
- 5 December 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 9 (6), 653-668
- https://doi.org/10.1109/tevc.2005.856210
Abstract
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.Keywords
This publication has 46 references indexed in Scilit:
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Towards the support of innovative conceptual design through interactive designer/evolutionary computing strategiesArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 2000
- Increasing Genomic Complexity by Gene Duplication and the Origin of VertebratesThe American Naturalist, 1999
- Evolving neural control systemsIEEE Expert, 1995
- Discovering Complex Othello Strategies through Evolutionary Neural NetworksConnection Science, 1995
- Analog computation via neural networksTheoretical Computer Science, 1994
- Learning and Evolution in Neural NetworksAdaptive Behavior, 1994
- An evolutionary algorithm that constructs recurrent neural networksIEEE Transactions on Neural Networks, 1994
- Genetic evolution of the topology and weight distribution of neural networksIEEE Transactions on Neural Networks, 1994
- Mathematical GamesScientific American, 1962