This site has been permanently archived. This is a static copy provided by the University of Southampton.

%A Xiao Huang %A John Weng %T Novelty and Reinforcement Learning in the Value System of Developmental Robots %X The value system of a developmental robot signals the occurrence of salient sensory inputs, modulates the mapping from sensory inputs to action outputs, and evaluates candidate actions. In the work reported here, a low level value system is modeled and implemented. It simulates the non-associative animal learning mechanism known as habituation effect. Reinforcement learning is also integrated with novelty. Experimental results show that the proposed value system works as designed in a study of robot viewing angle selection. %K developmental robot, value system, sensory, habituation effect, reinforcement learning, IHDR, SAIL %P 47-55 %E Christopher G. Prince %E Yiannis Demiris %E Yuval Marom %E Hideki Kozima %E Christian Balkenius %V 94 %D 2002 %I Lund University Cognitive Studies %L cogprints2511