de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Poster

Reinforcement learning for optimal control of arm movements

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84135

Peters,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons84963

Schaal,  S
Max Planck Institute for Biological Cybernetics, Max Planck Society;

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

Theodorou, E., Peters, J., & Schaal, S. (2007). Reinforcement learning for optimal control of arm movements. Poster presented at 37th Annual Meeting of the Society for Neuroscience (Neuroscience 2007), San Diego, CA, USA.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-CB43-6
Abstract
Every day motor behavior consists of a plethora of challenging motor skills from discrete movements such as reaching and throwing to rhythmic movements such as walking, drumming and running. How this plethora of motor skills can be learned remains an open question. In particular, is there any unifying computational framework that could model the learning process of this variety of motor behaviors and at the same time be biologically plausible? In this work we aim to give an answer to these questions by providing a computational framework that unifies the learning mechanism of both rhythmic and discrete movements under optimization criteria, i.e., in a non-supervised trial and error fashion. Our suggested framework is based on Reinforcement Learning, which is mostly considered as too costly to be a plausible mechanism for learning complex limb movement. However, recent work on reinforcement learning with policy gradients combined with parameterized movement primitives allows novel and more efficient algorithms. By using the representational power of such motor primitives we show how rhythmic motor behaviors such as walking, squashing and drumming as well as discrete behaviors like reaching and grasping can be learned with biologically plausible algorithms. Using extensive simulations and by using different reward functions we provide results that support the hypothesis that Reinforcement Learning could be a viable candidate for motor learning of human motor behavior when other learning methods like supervised learning are not feasible.