Sciweavers

11 search results - page 2 / 3
» Learning in Reactive Environments with Arbitrary Dependence
Sort
View
MFCS
1995
Springer
13 years 8 months ago
An Abstract Account of Composition
act Account of Composition Mart n Abadi1 and Stephan Merz2 1 Digital Equipment Corporation, Systems Research Center, 130 Lytton Avenue, Palo Alto, CA 94301, U.S.A. 2 Institut fur I...
Martín Abadi, Stephan Merz
DAGM
2010
Springer
13 years 5 months ago
Learning of Optimal Illumination for Material Classification
We present a method to classify materials in illumination series data. An illumination series is acquired using a device which is capable to generate arbitrary lighting environment...
Markus Jehle, Christoph Sommer, Bernd Jähne
ATAL
2007
Springer
13 years 11 months ago
Model-based function approximation in reinforcement learning
Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
Nicholas K. Jong, Peter Stone
ML
2002
ACM
143views Machine Learning» more  ML 2002»
13 years 5 months ago
A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes
An issue that is critical for the application of Markov decision processes MDPs to realistic problems is how the complexity of planning scales with the size of the MDP. In stochas...
Michael J. Kearns, Yishay Mansour, Andrew Y. Ng
SAC
2004
ACM
13 years 10 months ago
Combining analysis and synthesis in a model of a biological cell
for ideas, and then abstract away from these ideas to produce algorithmic processes that can create problem solutions in a bottom-up manner. We have previously described a top-dow...
Ken Webb, Tony White