neural networks research group
areas
people
projects
demos
publications
software/data
Incorporating Advice into Evolution of Neural Networks (2005)
Chern Han Yong
,
Kenneth O. Stanley
, and
Risto Miikkulainen
Neuroevolution is a promising learning method in tasks with extremely large state and action spaces and hidden states. Recent advances allow neuroevolution to take place in real time, making it possible to e.g. construct video games with adaptive agents. Often some of the desired behaviors for such agents are known, and it would make sense to prescribe them, rather than requiring evolution to discover them. This paper presents a technique for incorporating human-generated advice in real time into neuroevolution. The advice is given in a formal language and converted to a neural network structure through KBANN. The NEAT neuroevolution method then incorporates the structure into existing networks through evolution of network weights and topology. The method is evaluated in the NERO video game, where it makes learning faster even when the tasks change and novel ways of making use of the advice are required. Such ability to incorporate human knowledge into neuroevolution in real time may prove useful in several interactive adaptive domains in the future.
View:
PDF
Citation:
In
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2005)
, 2005. Late Breaking Papers.
Bibtex:
@inproceedings{yong:gecco05lbp, title={Incorporating Advice into Evolution of Neural Networks}, author={Chern Han Yong and Kenneth O. Stanley and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2005)}, note={Late Breaking Papers}, url="http://nn.cs.utexas.edu/?yong:gecco05lbp", year={2005} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Kenneth Stanley
Postdoctoral Alumni
kstanley [at] cs ucf edu
Chern Han Yong
Masters Alumni
cherny [at] nus edu sg
Projects
NEAT: Evolving Increasingly Complex Neural Network Topologies
2000 - 2011
NERO: NeuroEvolving Robotic Operatives
2003 - 2009
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning
Game Playing