Sciweavers

373 search results - page 4 / 75
» Covariant Policy Search
Sort
View
NIPS
2003
13 years 9 months ago
Policy Search by Dynamic Programming
We consider the policy search approach to reinforcement learning. We show that if a “baseline distribution” is given (indicating roughly how often we expect a good policy to v...
J. Andrew Bagnell, Sham Kakade, Andrew Y. Ng, Jeff...
PR
2002
202views more  PR 2002»
13 years 7 months ago
Illumination color covariant locale-based visual object retrieval
Search by Object Model -- finding an object inside a target image -- is a desirable and yet difficult mechanism for querying multimedia data. An added difficulty is that objects c...
Mark S. Drew, Ze-Nian Li, Zinovi Tauber
ICASSP
2011
IEEE
12 years 11 months ago
Clustering of bootstrapped acoustic model with full covariance
HMM-based acoustic models built from bootstrap are generally very large, especially when full covariance matrices are used for Gaussians. Therefore, clustering is needed to compac...
Xin Chen, Xiaodong Cui, Jian Xue, Peder Olsen, Joh...
GECCO
2010
Springer
160views Optimization» more  GECCO 2010»
14 years 16 days ago
Benchmarking a weighted negative covariance matrix update on the BBOB-2010 noisy testbed
In a companion paper, we presented a weighted negative update of the covariance matrix in the CMA-ES—weighted active CMA-ES or, in short, aCMA-ES. In this paper, we benchmark th...
Nikolaus Hansen, Raymond Ros
GECCO
2010
Springer
165views Optimization» more  GECCO 2010»
13 years 9 months ago
Evolving robust controller parameters using covariance matrix adaptation
In this paper, the advantages of introducing an additional amount of tests when evolving parameters for specific purposes is discussed. A set of optimal PID-controller parameters...
Gerulf K. M. Pedersen, Martin V. Butz