UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Real-Time Learning in the NERO Video Game (2005)
Kenneth O. Stanley
,
Ryan Cornelius
,
Risto Miikkulainen
,
Thomas D'Silva
, and
Aliza Gold
If game characters could learn through interacting with the player, behavior could improve as the game is played, keeping it interesting. The real-time NeuroEvolution of Augmenting Topologies (rtNEAT) method, which can evolve increasingly complex artificial neural networks in real time as a game is being played, will be presented. The rtNEAT method makes possible an entirely new genre of video games in which the player trains a team of agents through a series of customized exercises. In order 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. The live demo will show how agents in NERO adapt in real time as they interact with the player. In the future, rtNEAT may allow new kinds of educational and training applications through interactive and adapting games.
View:
PDF
Citation:
In
Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2005) Demo Papers
2005.
Bibtex:
@InProceedings{stanley:aiide05, title={Real-Time Learning in the NERO Video Game}, author={Kenneth O. Stanley and Ryan Cornelius and Risto Miikkulainen and Thomas D'Silva and Aliza Gold}, booktitle={Proceedings of the Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2005) Demo Papers}, url="http://www.cs.utexas.edu/users/ai-lab?stanley:aiidedemo05", year={2005} }
People
Ryan Cornelius
Undergraduate Alumni
Thomas D'Silva
Masters Alumni
twdsilva [at] gmail com
Aliza Gold
Formerly affiliated Collaborator
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Kenneth Stanley
Postdoctoral Alumni
kstanley [at] cs ucf edu
Projects
NERO: NeuroEvolving Robotic Operatives
2003 - 2009
NEAT: Evolving Increasingly Complex Neural Network Topologies
2000 - 2011
Areas of Interest
Applications
Evolutionary Computation
Game Playing
Neuroevolution
Reinforcement Learning
Software/Data
rtNEAT C++
The rtNEAT package contains source code implementing the real-time NeuroEvolution of Augmenting Topologies method. In ad...
2006
Demos
Neuro-Evolving Robotic Operatives (NERO)
Kenneth Stanley
2007
Labs
Neural Networks