Back to Results
First PageMeta Content
Statistics / Dynamic programming / Stochastic control / Reinforcement learning / Robotics / Optimal control / Hamilton–Jacobi–Bellman equation / Machine learning / Tendon / Cybernetics / Control theory / Science


Tendon-Driven Variable Impedance Control Using Reinforcement Learning Eric Rombokas, Mark Malhotra, Evangelos Theodorou, Emanuel Todorov, and Yoky Matsuoka Abstract—Biological motor control is capable of learning compl
Add to Reading List

Document Date: 2013-06-10 06:15:02

Open Document

File Size: 996,54 KB

Share Result on Facebook

City

Cambridge / New York / /

Company

MIT Press / Krieger Publishing Co. Inc. / B. H. Brown D. D. / Evolvable Systems / /

Currency

pence / /

Facility

University of Southern California / /

IndustryTerm

model-free reinforcement learning algorithm / tendon-driven systems / torque-driven systems / tendon-driven robotic systems / antagonistic systems / fine object manipulation using tendon-driven systems / free energy dualities / tendon travel / silicon rubber skin / nonlinear stochastic systems / human tendon network / tendon network / biomimetic systems / robotic systems / tendon networks / learning algorithm / /

Organization

University of Southern California / MIT / FDP FDS / /

Person

Emanuel Todorov / Yoky Matsuoka Abstract / Andrew G. Barto / Richard S. Sutton / Learning Eric Rombokas / P. Dorato / V / Mark Malhotra / Evangelos Theodorou / /

/

Position

proportional controller / constant-gain proportional controller / time-varying impedance controller / feedback controller / controller / general-purpose PID controller / /

ProvinceOrState

Southern California / New York / /

PublishedMedium

The International Journal / Journal of Machine Learning Research / Journal of Neuroscience / /

Region

Southern California / /

Technology

Neuroscience / learning algorithm / PI2 algorithm / machine learning / model-free reinforcement learning algorithm / /

URL

http /

SocialTag