Sciweavers

5114 search results - page 170 / 1023
» Learning for Evolutionary Design
Sort
View
ICML
1998
IEEE
16 years 4 months ago
Genetic Programming and Deductive-Inductive Learning: A Multi-Strategy Approach
Genetic Programming (GP) is a machine learning technique that was not conceived to use domain knowledge for generating new candidate solutions. It has been shown that GP can bene ...
Ricardo Aler, Daniel Borrajo, Pedro Isasi
GECCO
2009
Springer
135views Optimization» more  GECCO 2009»
15 years 9 months ago
Neuroevolutionary reinforcement learning for generalized helicopter control
Helicopter hovering is an important challenge problem in the field of reinforcement learning. This paper considers several neuroevolutionary approaches to discovering robust cont...
Rogier Koppejan, Shimon Whiteson
AAMAS
2007
Springer
15 years 9 months ago
Bifurcation Analysis of Reinforcement Learning Agents in the Selten's Horse Game
Abstract. The application of reinforcement learning algorithms to multiagent domains may cause complex non-convergent dynamics. The replicator dynamics, commonly used in evolutiona...
Alessandro Lazaric, Jose Enrique Munoz de Cote, Fa...
IWCLS
2007
Springer
15 years 9 months ago
On Lookahead and Latent Learning in Simple LCS
Learning Classifier Systems use evolutionary algorithms to facilitate rule- discovery, where rule fitness is traditionally payoff based and assigned under a sharing scheme. Most c...
Larry Bull
CW
2003
IEEE
15 years 8 months ago
Virtual Experiment Environments Design for Science Education
Virtual reality technology is reported that the use of virtual reality(VR) as an educational tool can increase student interests, understanding and creative learning because of en...
Young-suk Shin