Sciweavers

84 search results - page 6 / 17
» Integrating Reinforcement Learning, Bidding and Genetic Algo...
Sort
View
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
14 years 16 days 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
AAAI
1996
13 years 8 months ago
Evolution-Based Discovery of Hierarchical Behaviors
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive genera...
Justinian P. Rosca, Dana H. Ballard
GECCO
2009
Springer
142views Optimization» more  GECCO 2009»
13 years 11 months ago
Evolution, development and learning using self-modifying cartesian genetic programming
Self-Modifying Cartesian Genetic Programming (SMCGP) is a form of genetic programming that integrates developmental (self-modifying) features as a genotype-phenotype mapping. This...
Simon Harding, Julian Francis Miller, Wolfgang Ban...
CORR
2002
Springer
100views Education» more  CORR 2002»
13 years 6 months ago
A neural model for multi-expert architectures
We present a generalization of conventional artificial neural networks that allows for a functional equivalence to multi-expert systems. The new model provides an architectural fr...
Marc Toussaint
CEC
2007
IEEE
14 years 1 months ago
Combine and compare evolutionary robotics and reinforcement Learning as methods of designing autonomous robots
—The purpose of this paper is to present a comparison between two methods of building adaptive controllers for robots. In spite of the wide range of techniques which are used for...
Sergiu Goschin, Eduard Franti, Monica Dascalu, San...