Back to Results
First PageMeta Content
Estimation theory / Reinforcement learning / Expectation–maximization algorithm / Linear regression / Humanoid robot / Supervised learning / Stability / Q-learning / Statistics / Machine learning / Learning


Reinforcement Learning by Reward-weighted Regression for Operational Space Control Jan Peters Max-Planck Institute for Biological Cybernetics, 72074 Tuebingen, Germany
Add to Reading List

Document Date: 2011-01-31 11:48:40

Open Document

File Size: 398,91 KB

Share Result on Facebook

City

Tuebingen / Hoboken / /

Company

Kaebling L. P. / /

Country

Jordan / /

/

Facility

Max-Planck Institute / Germany Stefan Schaal University of Southern California / /

IndustryTerm

convex solution / random search / analytical solution / invalid solutions / statistical learning algorithm / analytical solutions / online learning / smooth online improvement / consistent solution / arbitrary solutions / learning solution / robotic systems / dimensional robot systems / nominal control law a0 / Robot dynamics algorithms / random search algorithms / real-time improvement / online learning control / energy consumption / broader applications / reinforcement learning algorithms / randomized search algorithms / genetic algorithms / appropriate learning algorithms / analytic solution / online learning method scales / linear systems / stochastic search / learning algorithm / control law / /

Organization

University of Southern California / Los Angeles / Applied Intelligence / U.S. Securities and Exchange Commission / Institute for Biological Cybernetics / /

Person

Jan Peters / /

/

Position

local controller / appropriate operational space controller / author / learning controller / locally linear forward / Mosaic model for sensorimotor learning and control / controller / distal teacher / /

ProvinceOrState

Southern California / California / /

PublishedMedium

Machine Learning / Journal of Artificial Intelligence Research / Journal of Cognitive Neuroscience / /

Region

Southern California / /

Technology

ensuing EM algorithm / Neuroscience / improved algorithm / Machine Learning / Robot dynamics algorithms / LWPR learning algorithm / presented algorithm / learning algorithm / reinforcement learning algorithms / statistical learning algorithm / random search algorithms / resulting algorithm / randomized search algorithms / ARP algorithms / simulation / 1 An EM algorithm / methods employing EM-style algorithms / appropriate learning algorithms / /

SocialTag