Sciweavers

275 search results - page 43 / 55
» Online Stochastic and Robust Optimization
Sort
View
ICRA
2010
IEEE
145views Robotics» more  ICRA 2010»
13 years 6 months ago
Reinforcement learning of motor skills in high dimensions: A path integral approach
— Reinforcement learning (RL) is one of the most general approaches to learning control. Its applicability to complex motor systems, however, has been largely impossible so far d...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
PAMI
2010
238views more  PAMI 2010»
13 years 6 months ago
Tracking Motion, Deformation, and Texture Using Conditionally Gaussian Processes
—We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, ...
Tim K. Marks, John R. Hershey, Javier R. Movellan
JMLR
2010
148views more  JMLR 2010»
13 years 2 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
IOLTS
2008
IEEE
117views Hardware» more  IOLTS 2008»
14 years 2 months ago
Verification and Analysis of Self-Checking Properties through ATPG
Present and future semiconductor technologies are characterized by increasing parameters variations as well as an increasing susceptibility to external disturbances. Transient err...
Marc Hunger, Sybille Hellebrand
JMLR
2008
159views more  JMLR 2008»
13 years 7 months ago
Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies
When monitoring spatial phenomena, which can often be modeled as Gaussian processes (GPs), choosing sensor locations is a fundamental task. There are several common strategies to ...
Andreas Krause, Ajit Paul Singh, Carlos Guestrin