English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Poster

Reinforcement Learning of Perceptual Coupling for Motor Primitives

MPS-Authors
/persons/resource/persons84021

Kober,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84135

Peters,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Kober, J., & Peters, J. (2008). Reinforcement Learning of Perceptual Coupling for Motor Primitives. Poster presented at 8th European Workshop on Reinforcement Learning for Robotics (EWRL 2008), Villeneuve d’Ascq, France.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-C885-A
Abstract
Reinforcement learning is a natural choice for the learning of complex motor tasks by reward-related self-improvement. As the space of movements is high-dimensional and continuous, a policy parametrization is needed which can be used in this context. Traditional motor primitive approaches deal largely with open-loop policies which can only deal with small perturbations. In this paper, we present a new type of motor primitive policies which serve as closed-loop policies together with an appropriate learning algorithm. Our new motor primitives are an augmented version version of the dynamic systems motor primitives that incorporates perceptual coupling to external variables. We show that these motor primitives can perform complex tasks such a Ball-in-a-Cup or Kendama task even with large variances in the initial conditions where a human would hardly be able to learn this task. We initialize the open-loop policies by imitation learning and the perceptual coupling with a handcrafted solution. We first improve the open-loop policies and subsequently the perceptual coupling using a novel reinforcement learning method which is particularly well-suited for motor primitives.