Back to Results
First PageMeta Content
Systems science / Youla–Kucera parametrization / Adaptive control / Optimal control / Nonlinear control / Model predictive control / Kalman filter / Robust control / Automatic control / Control theory / Systems theory / Cybernetics


Feedback Controller Parameterizations for Reinforcement Learning John W. Roberts Ian R. Manchester
Add to Reading List

Document Date: 2011-02-22 01:10:59

Open Document

File Size: 226,05 KB

Share Result on Facebook

City

Boston / Baltimore / New York / New Haven / /

Company

Macmillan Publishing Company / Neural Information Processing Systems / Multivariable Systems E. Decentralized Systems / Princeton Press / D. Nonlinear Systems / SIAM Journal / Youla Parameterization / /

/

Facility

stable Q / Prentice Hall / Yale University / /

IndustryTerm

statistical gradient-following algorithms / stability critical systems / online learning / stable nonlinear operator / policy gradient algorithms / direct policy search / chosen control law / stable systems / much more complex systems / feedback systems / Policy search / online system identification / bounded energy signals / nonlinear systems / hardware-in-theloop learning systems / stable linear systems / controls applications / nonlinear and uncertain systems / linear systems / learning algorithm / /

Organization

National Science Foundation / MIT / eta / Yale / Yale University / /

Person

Teresa Weirui Zhang / J. Zico Kolter / Varun Ganapathi / Joao P. Hespanha / A. Stephen Morse / Ian R. Manchester Russ Tedrake / Allen R. Tannenbaum / Adam Coates / Brian D.O. Anderson / Auke Ijspeert / H. Sebastian Seung / Bruce A. Francis / Pieter Abbeel / R.J. Williams / Daniel Liberzon / Morgan Quigley / John N. Tsitsiklis / Lionel Moret / E. F. Camacho / Craig H. Barratt / Stefan Schaal / Carlos Bordons / Jun Zhang / Andrew Y. Ng / Wei-Min Lu / Stephen P. Boyd / John C. Doyle / Fixing / John W. Roberts / Aude Billard / J. Bongiorno Jr. / Vincent D. Blondel / Russ Tedrake / John W. Roberts Ian / /

Position

LQR controller / additional controller / general controller / individual controller / unstable controller / decentralized controller / LQR Cost Matrix controller / initial LQR controller / stabilizing linear controller / designer / linear controller / resulting controller / inappropriate controller / linear feedback controller / Feedback Controller / Controller / Observer / /

ProvinceOrState

Maryland / New York / Connecticut / /

PublishedMedium

Machine Learning / Journal of Fluid Mechanics / /

Technology

policy gradient algorithms / 3 Cost The algorithm / Machine Learning / statistical gradient-following algorithms / resulting learning algorithm / /

SocialTag