— We are interested in transferring control policies for arbitrary tasks from a human to a robot. Using interactive demonstration via teloperation as our transfer scenario, we ca...
Abstract--A prominent emerging theory of sensorimotor development in biological systems proposes that control knowledge is encoded in the dynamics of physical interaction with the ...
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Intelligent planning algorithms such as the Partially Observable Markov Decision Process (POMDP) have succeeded in dialog management applications [10, 11, 12] because of their rob...
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...