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.

In this paper we describe a physical and virtual space for conducting research into intelligent mobile sensor networks. Intelligent mobile sensor networks present a number of difficult theoretical and practical research challenges. We design an imaginative environment that can be used to explore, test, analyse and compare theoretical and practical approaches to representing and grounding knowledge derived from the sensor data of an intelligent mobile sensor network.Mobile sensor networks not only capture information from the environment, but they also need to model their physical environment in order to move around it safely and effectively. As an intelligent mobile sensor roams a physical space it is bombarded with sensory information from which it tries to construct an abstract and compact world model. Intelligent mobile sensors like robots can develop a rich world model through interaction with both physical objects and the rich information resources accessible on the Semantic Web.We have designed an interactive learning space which is made up of both physical objects and information resources on the web. It will allow the study of intelligent mobile sensor networks, their grounding, knowledge representation, reasoning, communication, collaboration, interactive learning capabilities, and potential business applications.

No abstract

No abstract