Homeokinetic Reinforcement Learning

Smith, Simón C.; Herrmann, J. Michael

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.

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: First IAPR TC3 Workshop, PSL 2011
• Start Date: Sep 15, 2011
• End Date: Sep 16, 2011
• Online Publication Date: Feb 9, 2012
• Publication Date: 2012
• Deposit Date: Jul 11, 2023
• Publisher: Springer
• Pages: 82-91
• Series Title: Lecture Notes in Computer Science
• Series Number: 7081
• Series ISSN: 0302-9743
• Book Title: Partially Supervised Learning. PSL 2011
• ISBN: 978-3-642-28257-7
• DOI: https://doi.org/10.1007/978-3-642-28258-4_9