Confidence-Based Progress-Driven Self-Generated Goals for Skill Acquisition in Developmental Robots

Confidence-Based Progress-Driven Self-Generated Goals for Skill Acquisition in Developmental Robots

A reinforcement learning agent that autonomously explores its environment can utilize a curiosity drive to enable continual learning of skills, in the absence of any external rewards. We formulate curiosity-driven exploration, and eventual skill acquisition, as a selective sampling problem. Each e...

Full description

Bibliographic Details
Main Authors: Hung eNgo, Matthew eLuciw, Alexander eFörster, Jürgen eSchmidhuber
Format: Article
Language:English
Published: Frontiers Media S.A. 2013-11-01
Series:Frontiers in Psychology
Subjects:
developmental robotics
Active Learning
artificial curiosity
markov decision processes
Online Learning
intrinsic motivation
Online Access:http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00833/full

Internet

http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00833/full

Similar Items