Sciweavers

13717 search results - page 2510 / 2744
» Control Systems
Sort
View
124
Voted
ICML
1994
IEEE
15 years 7 months ago
A Modular Q-Learning Architecture for Manipulator Task Decomposition
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
Chen K. Tham, Richard W. Prager
OOPSLA
1987
Springer
15 years 7 months ago
Metaclasses are First Class: the ObjVlisp Model
This paper shows how an attempt at a uniform and reflective definition resulted in an open-ended system supporting ObjVlisp, which we use to simulate object-oriented language exte...
Pierre Cointe
142
Voted
ASM
2010
ASM
15 years 6 months ago
Starting B Specifications from Use Cases
The B method is one of the most used formal methods, when reactive systems is under question, due to good support for refinement. However, obtaining the formal model from requireme...
Thiago C. de Sousa, Aryldo G. Russo
132
Voted
GECCO
2010
Springer
187views Optimization» more  GECCO 2010»
15 years 6 months ago
Evolving agent behavior in multiobjective domains using fitness-based shaping
Multiobjective evolutionary algorithms have long been applied to engineering problems. Lately they have also been used to evolve behaviors for intelligent agents. In such applicat...
Jacob Schrum, Risto Miikkulainen
AVI
2008
15 years 5 months ago
Shadow tracking on multi-touch tables
Multi-touch interfaces have been a focus of research in recent years, resulting in development of various innovative UI concepts. Support for existing WIMP interfaces, however, sh...
Florian Echtler, Manuel Huber, Gudrun Klinker
« Prev « First page 2510 / 2744 Last » Next »