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

@misc{cogprints2511, volume = {94}, editor = {Christopher G. Prince and Yiannis Demiris and Yuval Marom and Hideki Kozima and Christian Balkenius}, title = {Novelty and Reinforcement Learning in the Value System of Developmental Robots}, author = {Xiao Huang and John Weng}, publisher = {Lund University Cognitive Studies}, year = {2002}, pages = {47--55}, keywords = {developmental robot, value system, sensory, habituation effect, reinforcement learning, IHDR, SAIL}, url = {http://cogprints.org/2511/}, abstract = {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.} }