283 search results - page 45 / 57 » Abstracting Reusable Cases from Reinforcement Learning |
COLT
2006
Springer
15 years 1 months ago
2006
Springer
Abstract. We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolut...
ECTEL
2006
Springer
15 years 1 months ago
2006
Springer
Abstract. There are specific sectors of the economy that can benefit from satellite-based tele-education. Areas, such as maritime and agriculture, share common needs for both broad...
ATAL
2010
Springer
14 years 9 months ago
2010
Springer
We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned obje...
COOPIS
2004
IEEE
15 years 1 months ago
2004
IEEE
Abstract. This paper introduces ThreadMill - a distributed and parallel component architecture for applications that process large volumes of streamed (time-sequenced) data, such a...
FUIN
2008
14 years 9 months ago
2008
A deterministic behavior of systems composed of several modules is a desirable design goal. Assembling a complex system from components requires also a high degree of re-usability....