Variable Impedance Control A Reinforcement Learning Approach Jonas Buchli, Evangelos Theodorou, Freek Stulp, Stefan Schaal Abstract— One of the hallmarks of the performance, versatility, and robustness of biological mo - Biological process - Document - PDFSEARCH.IO - Document Search Engine

Back to Results

First Page	Meta Content
	Variable Impedance Control A Reinforcement Learning Approach Jonas Buchli, Evangelos Theodorou, Freek Stulp, Stefan Schaal Abstract— One of the hallmarks of the performance, versatility, and robustness of biological mo Add to Reading List Document Date: 2011-02-17 00:49:52 Open Document File Size: 387,10 KB Share Result on Facebook City II / Boston / New York / Berlin / III / Cambridge / London / / Company Neural Information Processing Systems / MIT Press / John Wiley & Sons Inc. / Linear And Optimal Control Systems / Elsevier Publishing Company / Mti / / Currency pence / / Facility University of Southern California / / IndustryTerm simulated robot systems / continuous stateaction systems / inner product / dimensional dynamical systems / biological systems / reinforcement learning approach algorithm / final algorithm / nonlinear biological movement systems / nonlinear stochastic systems / proposed algorithm / robotic systems / simulated robotic systems / real-time control software package / reinforcement learning algorithm / motor systems / energy consumption / multi-agent systems / dimensional robotic systems / stochastic multi-agent systems / control systems / multi degree-of-freedom control systems / nonlinear systems / real robotic systems / invariant systems / hybrid differential dynamic programming algorithm / stochastic dynamical systems / control solution / learning algorithm / learning algorithms / control law / / Organization MIT / University of Southern California / / Person M. Zefran / V / Evangelos Theodorou / / Position editor / rt / designer / immediate cost function rt / rigid body dynamics model / drop out / controller / / Product pseudo / / ProvinceOrState Southern California / New York / Massachusetts / / PublishedMedium Journal of Artificial Intelligence Research / Journal of Machine Learning Research / / Region Southern California / / Technology previous RL algorithms / PI2 learning algorithm / PI2 algorithm / 2010 algorithms / 2 ALGORITHM / PI algorithm / RL algorithms / outlined algorithms / machine learning / ONTROL WITH PI2 The PI2 algorithm / RL algorithm / A. The PI2 Algorithm The PI2 algorithm / PI2 algorithms / learning algorithm / hybrid differential dynamic programming algorithm / proposed algorithm / reinforcement learning approach algorithm / final algorithm / simulation / reinforcement learning algorithm / / SocialTag Mathematical optimization Dynamic programming Stochastic control Optimal control Operations research Reinforcement learning Robotics Humanoid robot Markov decision process Control theory