Sciweavers

4079 search results - page 734 / 816
» Neural Networks
Sort
View
ATAL
2007
Springer
15 years 7 months ago
Transfer via inter-task mappings in policy search reinforcement learning
The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have f...
Matthew E. Taylor, Shimon Whiteson, Peter Stone
103
Voted
ECAL
2007
Springer
15 years 7 months ago
Neuroevolution of Agents Capable of Reactive and Deliberative Behaviours in Novel and Dynamic Environments
Both reactive and deliberative qualities are essential for a good action selection mechanism. We present a model that embodies a hybrid of two very different neural network archit...
Edward Robinson, Timothy Ellis, Alastair Channon
ECAL
2007
Springer
15 years 7 months ago
New Models for Old Questions: Evolutionary Robotics and the 'A Not B' Error
Abstract. In psychology the ‘A not B’ error, whereby infants perseverate in reaching to the location where a toy was previously hidden after it has been moved to a new location...
Rachel Wood, Ezequiel A. Di Paolo
84
Voted
GECCO
2007
Springer
172views Optimization» more  GECCO 2007»
15 years 7 months ago
Acquiring evolvability through adaptive representations
Adaptive representations allow evolution to explore the space of phenotypes by choosing the most suitable set of genotypic parameters. Although such an approach is believed to be ...
Joseph Reisinger, Risto Miikkulainen
GECCO
2007
Springer
185views Optimization» more  GECCO 2007»
15 years 7 months ago
An informed convergence accelerator for evolutionary multiobjective optimiser
A novel optimisation accelerator deploying neural network predictions and objective space direct manipulation strategies is presented. The concept of directing the search through ...
Salem F. Adra, Ian Griffin, Peter J. Fleming