The benefits of boredom: An exploration in developmental robotics

Bolland, S. and Emami, S. (2007). The benefits of boredom: An exploration in developmental robotics. In: Artificial Life 2007 (ALIFE '07). IEEE Symposium on Artificial Life 2007 (ALIFE '07), Honolulu, Hawaii, U.S.A., (163-170). 1-5 April 2007. doi:10.1109/ALIFE.2007.367792


Author Bolland, S.
Emami, S.
Title of paper The benefits of boredom: An exploration in developmental robotics
Conference name IEEE Symposium on Artificial Life 2007 (ALIFE '07)
Conference location Honolulu, Hawaii, U.S.A.
Conference dates 1-5 April 2007
Proceedings title Artificial Life 2007 (ALIFE '07)
Journal name Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007
Place of Publication Piscataway, NJ, U.S.A.
Publisher IEEE - Institute of Electrical Electronics Engineers Inc.
Publication Year 2007
Sub-type Fully published paper
DOI 10.1109/ALIFE.2007.367792
ISBN 1-4244-0701-X
Start page 163
End page 170
Total pages 8
Language eng
Abstract/Summary Self-directed learning is an essential component of artificial and biological intelligent systems that are required to interact with and adapt to complex real world environments. Inspired by psychological and neuroscientific data, many algorithms and architectures have been proposed in the field of developmental robotics that use novelty as a training signal. Such approaches are aimed at motivating the exploration of sensory-motor contingencies for which mental models have not yet been accurately formed, driving the agent to develop task-independent competencies (such as understanding object affordances) without the need for explicit teaching. However, novelty-driven exploration on its own leads to a number of well-known problems that impede competence acquisition such as the attraction of agents to chaotic or unlearnable tasks and the temporary oversampling of aspects of the environment until they are no longer novel. This paper contributes to the field, taking insight from neuroscientific data on selective attention (particularly the temporary "boredom" associated with recently seen stimuli and a counter preference for the familiar), to propose mechanisms that may help address the noted problems relating to developmental learning in robots. Experiments conducted on an AIBO ERS-7 robotic dog demonstrate the potential of the approach
Subjects 1702 Cognitive Sciences
Keyword Self-directed learning
Artificial intelligent system
Developmental robotics
Neuroscientific data
Q-Index Code E1

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 1 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 07 Apr 2009, 23:18:50 EST by Maryanne Watson on behalf of School of Psychology