Oculo-motor stabilization reflexes: integration of inertial and visual information
Neural Networks - Special issue on neural control and robotics: biology and technology
New Robotics: Design Principles for Intelligent Systems
Artificial Life
On the information theoretic implications of embodiment - principles and methods
50 years of artificial intelligence
| Hi-index | 0.00 |
Animals show an abundance of different sensor morphologies, for example in insect compound eyes. However, the advantages of having highly specific sensor morphologies still remain unclear. In this paper we show that an appropriate sensor morphology can improve the learning performance of an agent's neural controller significantly. Using a sensor morphology that is "optimised" for a given task environment the agent is able to learn faster and to adapt more quickly to changes.