Sciweavers

SMC
2007
IEEE

Enhancing embodied evolution with punctuated anytime learning

13 years 10 months ago
Enhancing embodied evolution with punctuated anytime learning
—This paper discusses a new implementation of embodied evolution that uses the concept of punctuated anytime learning to increase the complexity of tasks that the learning system can solve. The basic idea is that there is one population of chromosomes per robot rather than one chromosome per robot and reproduction between robots involves a combination of two entire populations of chromosomes instead of the recombination of two single chromosomes. The embodied evolution with punctuated anytime learning system is compared with embodied evolution alone and evolutionary computation alone, as the three methods are used to solve a common problem. The results show that this new learning system is superior to the other methods for evolving colony robot control.
Gary B. Parker, Gregory E. Fedynyshyn
Added 04 Jun 2010
Updated 04 Jun 2010
Type Conference
Year 2007
Where SMC
Authors Gary B. Parker, Gregory E. Fedynyshyn
Comments (0)