— Ubiquitous robots need the ability to adapt their behaviour to the changing situations and demands they will encounter during their lifetimes. In particular, non-technical user...
— Libraries of trajectories are a promising way of creating policies for difficult problems. However, often it is not desirable or even possible to create a new library for ever...
Martin Stolle, Hanns Tappeiner, Joel E. Chestnutt,...
In the not too distant future Intelligent Creatures (robots, smart devices, smart vehicles, smart buildings, etc) will share the everyday living environment of human beings. It is...
Brendan Bartlett, Vladimir Estivill-Castro, Stuart...
— Reinforcement learning (RL) is one of the most general approaches to learning control. Its applicability to complex motor systems, however, has been largely impossible so far d...
— The paper proposes several improvements on the Direction of Gradient (DOG) algorithm proposed in [1] for detecting and localizing a biochemical source with moving sensors. In p...