| Popis: |
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 |
