163 search results - page 3 / 33 » Policy Gradient Methods for Robotics |
ICRA
2008
IEEE
14 years 1 months ago
2008
IEEE
— We examine the usefulness of passive compliance in a manipulator that learns contact motion. Based on the notice that humans outperforms robots with the contact motion, we foll...
RAS
2010
13 years 1 months ago
2010
ESANN
2008
13 years 8 months ago
2008
Natural policy gradient methods and the covariance matrix adaptation evolution strategy, two variable metric methods proposed for solving reinforcement learning tasks, are contrast...
ESANN
2007
13 years 8 months ago
2007
In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natur...
UAI
2008
13 years 8 months ago
2008
An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas m...