File(s) not publicly available
Evolving fixed-weight networks for learning robots
Recently research in the field of Evolutionary Robotics have begun to investigate the evolution of learning controllers for autonomous robots. Research in this area has achieved some promising results, but research to date has focussed on the evolution of neural networks incorporating synaptic plasticity. There has been little investigation of possible alternatives, although the importance of exploring such alternatives is recognised [7]. This paper describes a first step towards addressing this issue. Using networks with fixed synaoptic weights and 'leaky integrator' neurons, we evolve robot controllers capable of learning and thus exploiting regularities occurring within their environment.
History
Publication status
- Published
Publisher
IEEE PressPages
6.0Presentation Type
- paper
Event name
Proceedings Congress on Evolutionary Computation (CEC) 2002,Event location
Honolulu, Hawaii, USAEvent type
conferenceISBN
0-780-37282-4Department affiliated with
- Informatics Publications
Full text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2012-02-06Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC