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...
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: | |
Online Access: | http://journal.frontiersin.org/Journal/10.3389/fpsyg.2013.00833/full |
Similar Items
-
Curiosity Driven Reinforcement Learning for Motion Planning on Humanoids
by: Mikhail eFrank, et al.
Published: (2014-01-01) -
POWERPLAY: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem
by: Jürgen eSchmidhuber
Published: (2013-06-01) -
Learning tactile skills through curious exploration
by: Leo ePape, et al.
Published: (2012-07-01) -
Editorial: Intrinsically Motivated Open-Ended Learning in Autonomous Robots
by: Vieri Giuliano Santucci, et al.
Published: (2020-01-01) -
Computational mechanisms of curiosity and goal-directed exploration
by: Philipp Schwartenbeck, et al.
Published: (2019-05-01)