Sciweavers

69 search results - page 14 / 14
» icml 2000
Sort
View
ICML
2000
IEEE
14 years 5 months ago
Eligibility Traces for Off-Policy Policy Evaluation
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
ICML
2000
IEEE
14 years 5 months ago
Discovering Homogeneous Regions in Spatial Data through Competition
If all features causing heterogeneity were observed, a mixture of experts approach (Jacobs et al., 1991) is likely to be superior to using a single model. When unobserved or very n...
Slobodan Vucetic, Zoran Obradovic
ICML
2005
IEEE
14 years 5 months ago
Healing the relevance vector machine through augmentation
The Relevance Vector Machine (RVM) is a sparse approximate Bayesian kernel method. It provides full predictive distributions for test cases. However, the predictive uncertainties ...
Carl Edward Rasmussen, Joaquin Quiñonero Ca...
ICML
2010
IEEE
13 years 6 months ago
On the Consistency of Ranking Algorithms
We present a theoretical analysis of supervised ranking, providing necessary and sufficient conditions for the asymptotic consistency of algorithms based on minimizing a surrogate...
John Duchi, Lester W. Mackey, Michael I. Jordan