Back to Search Start Over

Simultaneous versus incremental learning of multiple skills by modular robots.

Authors :
Rossi, C.
Eiben, A.
Source :
Evolutionary Intelligence; Aug2014, Vol. 7 Issue 2, p119-131, 13p
Publication Year :
2014

Abstract

This paper is concerned with the problem of learning multiple skills by modular robots. The main question we address is whether it is better to learn multiple skills simultaneously (all-at-once) or incrementally (one-by-one). We conduct an experimental study with modular robots of various morphologies that need to acquire three different but correlated skills, efficient locomotion, navigation towards a target point, and obstacle avoidance, using a real-time, on-board evolution as the learning method. The results indicate that the one-by-one strategy is more efficient and more stable than the all-at-once strategy. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
18645909
Volume :
7
Issue :
2
Database :
Complementary Index
Journal :
Evolutionary Intelligence
Publication Type :
Academic Journal
Accession number :
97432466
Full Text :
https://doi.org/10.1007/s12065-014-0109-3