How not to be a black-box: evolution and genetic-engineering of high-level behaviours

In spite of many success stories in various domains, genetic algorithms and genetic programming still suffer from some significant pitfalls. Those evolved programs often lack important properties such as robustness, comprehensibility, transparency, modifiability and usability of domain knowledge easily available. We attempt to resolve these problems, at least in evolving high-level behaviours, by adopting a technique of conditions-and-behaviours originally used for minimizing the learning space in reinforcement learning. We experimentally validate the approach on a foraging task


Published in:
GECCO-99. Proceedings of the Genetic and Evolutionary Computation Conference. Joint Meeting of the Eighth International Conference on Genetic Algorithms (ICGA-99) and the Fourth Annual Genetic Programming Conference (GP-99), 1329-1335
Presented at:
Fourth Annual Genetic Programming Conference ,GP-99, Orlando, FL, USA, July, 1999
Year:
1999
Keywords:
Note:
Swiss Federal Inst. of Technol., Lausanne, Switzerland
Laboratories:




 Record created 2007-01-16, last modified 2018-03-17


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)