title: Novelty and Reinforcement Learning in the Value System of Developmental Robots creator: Huang, Xiao creator: Weng, John subject: Statistical Models subject: Machine Learning subject: Artificial Intelligence subject: Robotics description: 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. publisher: Lund University Cognitive Studies contributor: Prince, Christopher G. contributor: Demiris, Yiannis contributor: Marom, Yuval contributor: Kozima, Hideki contributor: Balkenius, Christian date: 2002 type: Conference Paper type: PeerReviewed format: application/pdf identifier: http://cogprints.org/2511/1/Huang.pdf identifier: Huang, Xiao and Weng, John (2002) Novelty and Reinforcement Learning in the Value System of Developmental Robots. [Conference Paper] relation: http://cogprints.org/2511/