neural networks research group
areas
people
projects
demos
publications
software/data
Human-Assisted Neuroevolution Through Shaping, Advice and Examples (2011)
Igor V. Karpov
,
Vinod K. Valsalam
and
Risto Miikkulainen
Many different methods for combining human expertise with machine learning in general, and evolutionary computation in particular, are possible. Which of these methods work best, and do they outperform human design and machine design alone? In order to answer this question, a human- subject experiment for comparing human-assisted machine learning methods was conducted. Three different approaches, i.e. advice, shaping, and demonstration, were employed to assist a powerful machine learning technique (neuroevolution) on a collection of agent training tasks, and contrasted with both a completely manual approach (scripting) and a completely hands-off one (neuroevolution alone). The results show that, (1) human-assisted evolution outperforms a manual scripting approach, (2) unassisted evolution performs consistently well across domains, and (3) different methods of assisting neuroevolution outperform unassisted evolution on different tasks. If done right, human-assisted neuroevolution can therefore be a powerful technique for constructing intelligent agents.
View:
PDF
,
PS
Citation:
In
Proceedings of the 13th Annual Genetic and Evolutionary Computation Conference (GECCO 2011)
, Dublin, Ireland, July 2011.
Bibtex:
@inproceedings{karpov:gecco11, title={Human-Assisted Neuroevolution Through Shaping, Advice and Examples}, author={Igor V. Karpov and Vinod K. Valsalam and Risto Miikkulainen}, booktitle={Proceedings of the 13th Annual Genetic and Evolutionary Computation Conference (GECCO 2011)}, month={July}, address={Dublin, Ireland}, url="http://nn.cs.utexas.edu/?karpov:gecco11", year={2011} }
People
Igor V. Karpov
Masters Alumni
ikarpov [at] gmail com
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Vinod Valsalam
Ph.D. Alumni
vkv [at] alumni utexas net
Projects
The OpenNERO AI Research and Education Platform
Since 2009
Neuroevolution in Real Time Games
Since 2005
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Leveraging Human Creativity with Machine Discovery
2008 - 2010
NERO: NeuroEvolving Robotic Operatives
2003 - 2009
Areas of Interest
Neuroevolution
Reinforcement Learning
Game Playing