Policy Learning for Motor Skills

Authors:
Jan Peters;Stefan Schaal
Affiliations:
Max-Planck Institute for Biological Cybernetics, Tübingen, 72074 and University of Southern California, Los Angeles, USA CA 90089;University of Southern California, Los Angeles, USA CA 90089 and ATR Computational Neuroscience Laboratory, Soraku-gun, Kyoto, Japan 619-0288
Venue:
Neural Information Processing
Year:
2008

Citing 3
Cited 0

Using expectation-maximization for reinforcement learning

Neural Computation
Modelling and Control of Robot Manipulators

Modelling and Control of Robot Manipulators
Natural actor-critic

ECML'05 Proceedings of the 16th European conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.