Recent Changes - Search:


University of Massachusetts


Motor Primitive Discovery

We present a method for autonomous on-line discovery of motor primitives for Markov decision processes with high-dimensional continuous action spaces. These biologically inspired motor primitives require overhead to compute but form a compressed representation of the action set that allows for improved performance on subsequent learning tasks that have similar dynamics.

Philip Thomas is a Ph.D candidate in the School of Computer Science at the University of Massachusetts Amherst, and is advised by Andrew G. Barto. He is a member of the Autonomous Learning Laboratory and received a MS and BS degree in computer science from Case Western Reserve University. His primary research interest is reinforcement learning.

Edit - History - Print - Recent Changes - Search
Page last modified on April 03, 2013, at 03:34 PM