| Document Date: 2009-08-27 12:26:43
Open Document File Size: 830,03 KBShare Result on Facebook
Company Baxter / / Facility Courant Institute / New York University / / IndustryTerm vanilla policy gradient algorithm / weight perturbation algorithm / real world systems / policy gradient algorithms / optimized policy gradient algorithm / model-free algorithms / Model-free reinforcement learning algorithms / energy cost / possible applications / policy gradient reinforcement learning algorithm / expected energy / learning algorithm / energy / / Organization New York University / Applied Math Lab / Courant Institute / / Person Jun Zhang / John W. Roberts / Russ Tedrake / / Position controller / / Technology policy gradient algorithms / learning algorithm / fluid dynamics / vanilla policy gradient algorithm / machine learning / policy gradient reinforcement learning algorithm / simulation / PG algorithms / WP algorithm / model-free algorithms / weight perturbation algorithm / Model-free reinforcement learning algorithms / optimized policy gradient algorithm / /
SocialTag |
Motor Learning at Intermediate Reynolds Number: Experiments with Policy Gradient on a Heaving Plate John W. Roberts, Jun Zhang and Russ Tedrake Abstract This work describes the development of a model-free reinforcement