Abstract— In this paper we study online gait optimization for modular robots. The learning strategy we apply is distributed, independent on robot morphology, and easy to implemen...
David Johan Christensen, Ulrik Pagh Schultz, Kaspe...
This paper presents an agent-based approach to assisting learners to dynamically adjust learning processes. The online learning process is first investigated where the importance ...
One aim of Meta-learning techniques is to minimize the time needed for problem solving, and the effort of parameter hand-tuning, by automating algorithm selection. The predictive m...
We propose a novel approach to designing algorithms for
object tracking based on fusing multiple observation models.
As the space of possible observation models is too large
for...
The authors propose a co-adaptive approach to controlling parameters for coevolution-based learning classifier systems. By taking advantage of the on-line incremental learning capa...