학술논문
Novelty and Reinforcement Learning in the Value System of Developmental Robots
Document Type
Conference Paper
Author
Source
Huang, Xiao and Weng, John (2002) Novelty and Reinforcement Learning in the Value System of Developmental Robots. [Conference Paper]
Subject
Language
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.