Sciweavers

27 search results - page 2 / 6
» Double-deck elevator systems using Genetic Network Programmi...
Sort
View
GECCO
2011
Springer
276views Optimization» more  GECCO 2011»
12 years 8 months ago
Evolution of reward functions for reinforcement learning
The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
Scott Niekum, Lee Spector, Andrew G. Barto
SMC
2007
IEEE
118views Control Systems» more  SMC 2007»
13 years 11 months ago
One-class learning with multi-objective genetic programming
One-class classification naturally only provides one class of exemplars on which to construct the classification model. In this work, multiobjective genetic programming (GP) all...
Robert Curry, Malcolm I. Heywood
GECCO
2007
Springer
213views Optimization» more  GECCO 2007»
13 years 11 months ago
Genetically programmed learning classifier system description and results
An agent population can be evolved in a complex environment to perform various tasks and optimize its job performance using Learning Classifier System (LCS) technology. Due to the...
Gregory Anthony Harrison, Eric W. Worden
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
13 years 10 months ago
Co-evolving recurrent neurons learn deep memory POMDPs
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Faustino J. Gomez, Jürgen Schmidhuber
IJCAI
2001
13 years 6 months ago
Neural Logic Network Learning using Genetic Programming
Neural Logic Network or Neulonet is a hybrid of neural network expert systems. Its strength lies in its ability to learn and to represent human logic in decision making using comp...
Chew Lim Tan, Henry Wai Kit Chia