Sciweavers

777 search results - page 66 / 156
» Learning dynamic algorithm portfolios
Sort
View
123
Voted
JUCS
2008
104views more  JUCS 2008»
15 years 2 months ago
Optimal Transit Price Negotiation: The Distributed Learning Perspective
: We present a distributed learning algorithm for optimizing transit prices in the inter-domain routing framework. We present a combined game theoretical and distributed algorithmi...
Dominique Barth, Loubna Echabbi, Chahinez Hamlaoui
115
Voted
IJCNN
2006
IEEE
15 years 8 months ago
On derivation of stagewise second-order backpropagation by invariant imbedding for multi-stage neural-network learning
— We present a simple, intuitive argument based on “invariant imbedding” in the spirit of dynamic programming to derive a stagewise second-order backpropagation (BP) algorith...
Eiji Mizutani, Stuart Dreyfus
119
Voted
CONSTRAINTS
2008
89views more  CONSTRAINTS 2008»
15 years 2 months ago
A Reinforcement Learning Approach to Interval Constraint Propagation
When solving systems of nonlinear equations with interval constraint methods, it has often been observed that many calls to contracting operators do not participate actively to th...
Frédéric Goualard, Christophe Jerman...
80
Voted
CIG
2005
IEEE
15 years 8 months ago
Utile Coordination: Learning Interdependencies Among Cooperative Agents
AbstractWe describe Utile Coordination, an algorithm that allows a multiagent system to learn where and how to coordinate. The method starts with uncoordinated learners and maintai...
Jelle R. Kok, Pieter Jan't Hoen, Bram Bakker, Niko...
GECCO
2003
Springer
114views Optimization» more  GECCO 2003»
15 years 7 months ago
Learning the Ideal Evaluation Function
Abstract. Designing an adequate fitness function requiressubstantial knowledge of a problem and of features that indicate progress towards a solution. Coevolution takes the human ...
Edwin D. de Jong, Jordan B. Pollack