Cogprints

Novelty and Reinforcement Learning in the Value System of Developmental Robots

Huang, Xiao and Weng, John (2002) Novelty and Reinforcement Learning in the Value System of Developmental Robots. [Conference Paper]

Full text available as:

[img]
Preview
PDF
405Kb

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.

Item Type:Conference Paper
Keywords:developmental robot, value system, sensory, habituation effect, reinforcement learning, IHDR, SAIL
Subjects:Computer Science > Statistical Models
Computer Science > Machine Learning
Computer Science > Artificial Intelligence
Computer Science > Robotics
ID Code:2511
Deposited By:Prince, Dr Christopher G.
Deposited On:04 Oct 2003
Last Modified:11 Mar 2011 08:55

Metadata

Repository Staff Only: item control page