Sciweavers

163 search results - page 30 / 33
» Policy Gradient Methods for Robotics
Sort
View
DAC
2009
ACM
14 years 2 months ago
Throughput optimal task allocation under thermal constraints for multi-core processors
It is known that temperature gradients and thermal hotspots affect the reliability of microprocessors. Temperature is also an important constraint when maximizing the performance...
Vinay Hanumaiah, Ravishankar Rao, Sarma B. K. Vrud...
IJRR
2008
139views more  IJRR 2008»
13 years 7 months ago
Learning to Control in Operational Space
One of the most general frameworks for phrasing control problems for complex, redundant robots is operational space control. However, while this framework is of essential importan...
Jan Peters, Stefan Schaal
ROBOCUP
2001
Springer
96views Robotics» more  ROBOCUP 2001»
14 years 8 days ago
Strategy Learning for a Team in Adversary Environments
Team strategy acquisition is one of the most important issues of multiagent systems, especially in an adversary environment. RoboCup has been providing such an environment for AI a...
Yasutake Takahashi, Takashi Tamura, Minoru Asada
ICARCV
2006
IEEE
147views Robotics» more  ICARCV 2006»
14 years 1 months ago
Scale Normalization for the Distance Maps AAM
— The Active Apearence Models (AAM) are often used in Man-Machine Interaction for their ability to align the faces. We propose a new normalization method for AAM based on distanc...
Denis Giri, Maxime Rosenwald, Benjamin Villeneuve,...
ICML
2007
IEEE
14 years 8 months ago
Cross-domain transfer for reinforcement learning
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
Matthew E. Taylor, Peter Stone