Curiosity Search: Producing Generalists by Encouraging Individuals to Continually Explore and Acquire Skills throughout Their Lifetime
Open Access
- 2 September 2016
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 11 (9) , e0162235
Abstract
Natural animals are renowned for their ability to acquire a diverse and general skill set over the course of their lifetime. However, research in artificial intelligence has yet to produce agents that acquire all or even most of the available skills in non-trivial environments. One candidate algorithm for encouraging the production of such individuals is Novelty Search, which pressures organisms to exhibit different behaviors from other individuals. However, we hypothesized that Novelty Search would produce sub-populations of specialists, in which each individual possesses a subset of skills, but no one organism acquires all or most of the skills. In this paper, we propose a new algorithm called Curiosity Search, which is designed to produce individuals that acquire as many skills as possible during their lifetime. We show that in a multiple-skill maze environment, Curiosity Search does produce individuals that explore their entire domain, while a traditional implementation of Novelty Search produces specialists. However, we reveal that when modified to encourage intra-life behavioral diversity, Novelty Search can produce organisms that explore almost as much of their environment as Curiosity Search, although Curiosity Search retains a significant performance edge. Finally, we show that Curiosity Search is a useful helper objective when combined with Novelty Search, producing individuals that acquire significantly more skills than either algorithm alone.Keywords
This publication has 33 references indexed in Scilit:
- A comparison of innovative problem-solving abilities between wild and captive spotted hyaenas, Crocuta crocutaAnimal Behaviour, 2013
- Confidence-based progress-driven self-generated goals for skill acquisition in developmental robotsFrontiers in Psychology, 2013
- Innovative problem solving by wild spotted hyenasProceedings Of The Royal Society B-Biological Sciences, 2012
- Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical StudyEvolutionary Computation, 2012
- Learning tactile skills through curious explorationFrontiers in Neurorobotics, 2012
- Abandoning Objectives: Evolution Through the Search for Novelty AloneEvolutionary Computation, 2011
- Genetic Diversity as an Objective in Multi-Objective Evolutionary AlgorithmsEvolutionary Computation, 2003
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Autonomous Mental Development by Robots and AnimalsScience, 2001
- Motivation reconsidered: The concept of competence.Psychological Review, 1959