Homeokinetic Reinforcement Learning

Simón C. Smith, J. Michael Herrmann

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In order to find a control policy for an autonomous robot by reinforcement learning, the utility of a behaviour can be revealed locally through a modulation of the motor command by probing actions. For robots with many degrees of freedom, this type of exploration becomes inefficient such that it is an interesting option to use an auxiliary controller for the selection of promising probing actions. We suggest here to optimise the exploratory modulation by a self-organising controller. The approach is illustrated by two control tasks, namely swing-up of a pendulum and walking in a simulated hexapod. The results imply that the homeokinetic approach is beneficial for high complexity problems.
Original languageEnglish
Title of host publicationPartially Supervised Learning: First IAPR TC3 Workshop, PSL 2011, Ulm, Germany, September 15-16, 2011, Revised Selected Papers
EditorsFriedhelm Schwenker, Edmondo Trentin
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Pages82-91
Number of pages10
ISBN (Electronic)978-3-642-28258-4
ISBN (Print)978-3-642-28257-7
DOIs
Publication statusPublished - 2012

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume7081
ISSN (Print)0302-9743

Fingerprint

Dive into the research topics of 'Homeokinetic Reinforcement Learning'. Together they form a unique fingerprint.

Cite this