Sciweavers

878 search results - page 70 / 176
» Learning to Control in Operational Space
Sort
View
CDC
2009
IEEE
138views Control Systems» more  CDC 2009»
15 years 1 months ago
Beyond local optimality: An improved approach to hybrid model learning
Abstract-- Local convergence is a limitation of many optimization approaches for multimodal functions. For hybrid model learning, this can mean a compromise in accuracy. We develop...
Stephanie Gil, Brian Williams
IROS
2007
IEEE
144views Robotics» more  IROS 2007»
15 years 10 months ago
Bipedal walking on rough terrain using manifold control
— This paper presents an algorithm for adapting periodic behavior to gradual shifts in task parameters. Since learning optimal control in high dimensional domains is subject to t...
Tom Erez, William D. Smart
148
Voted
IJVR
2007
108views more  IJVR 2007»
15 years 3 months ago
Design and Narrative Structure for the Virtual Human Scenarios
—This article describes the design of the two application scenarios of the Virtual Human project and its integration into the Virtual Human system. This includes overall concepts...
Stefan Göbel, Ido Aharon Iurgel, Markus R&oum...
CEC
2007
IEEE
15 years 8 months ago
Double-deck elevator systems using Genetic Network Programming with reinforcement learning
Abstract-- In order to increase the transportation capability of elevator group systems in high-rise buildings without adding elevator installation space, double-deck elevator syst...
Jin Zhou, Lu Yu, Shingo Mabu, Kotaro Hirasawa, Jin...
AAAI
1998
15 years 5 months ago
Applying Online Search Techniques to Continuous-State Reinforcement Learning
In this paper, we describe methods for e ciently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boo...
Scott Davies, Andrew Y. Ng, Andrew W. Moore