Sciweavers

3381 search results - page 91 / 677
» LEO - DB2's LEarning Optimizer
Sort
View
CDC
2010
IEEE
105views Control Systems» more  CDC 2010»
13 years 5 months ago
Learning in mean-field oscillator games
This research concerns a noncooperative dynamic game with large number of oscillators. The states are interpreted as the phase angles for a collection of non-homogeneous oscillator...
Huibing Yin, Prashant G. Mehta, Sean P. Meyn, Uday...
ICML
2003
IEEE
14 years 11 months ago
The Cross Entropy Method for Fast Policy Search
We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...
Shie Mannor, Reuven Y. Rubinstein, Yohai Gat
GECCO
2000
Springer
121views Optimization» more  GECCO 2000»
14 years 1 months ago
Metaphor for learning: an evolutionary algorithm
The organizational algorithm is examined as a computational approach to representing interpersonal learning. The structure of the algorithm is introduced and described in context ...
Jody Lee Louse, Alexander Kain, James Hines
ICML
2006
IEEE
14 years 11 months ago
Agnostic active learning
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the ass...
Maria-Florina Balcan, Alina Beygelzimer, John Lang...
ICML
1998
IEEE
14 years 11 months ago
The MAXQ Method for Hierarchical Reinforcement Learning
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Thomas G. Dietterich