Motor Learning on a Heaving Plate via Improved-SNR Algorithms

Abstract

Creatures in nature have subtle and complicated interactions with their surrounding fluids, achieving levels of performance as yet unmatched by engineered solutions. Model-free reinforcement learning (MFRL) holds the promise of allowing man-made controllers to take advantage of the subtlety of fluid-body interactions solely using data gathered on the actual… (More)

Topics

Cite this paper

@inproceedings{Roberts2009MotorLO, title={Motor Learning on a Heaving Plate via Improved-SNR Algorithms}, author={John W. Roberts and Russ Tedrake and John T. Roberts}, year={2009} }