In almost all real systems where reinforcement learning is applied, it is found that a
knowledge free approach doesn't work. The basic RL algorithms must sufficiently be biased …

Reinforcement learning has been repeatedly suggested as good candidate for learning in
robotics. However, the large search spaces normally occurring robotics and expensive …

In the quest for machines that are able to learn, reinforcement learning (RL) is found to be an
appealing learning methodology. A known problem in this learning method, however is that …

The required learning time and curse of dimensionality restrict the applicability of
Reinforcement Learning (RL) on real robots. Difficulty in inclusion of initial knowledge and …

This paper proposes a reinforcement learning architecture containing multiple “experts”,
each of which is a specialist in a different region in the overall state space. The central idea …

Reinforcement learning (Kaelbling et al., 1996; Sutton & Barto, 1998) is a machine learning
technique that automatically acquires a good action policy, ie a mapping from the current …

A tabula rasa learning technique has worked well in well defined grid like problems (Barto et
al., 1993). Nevertheless, it has severe limitations when applied in complex domains. In order …

Autonomous robot systems operating in an uncertain environment have to be able to cope
with new situations and task requirements. Important properties of the control architecture of …

The behaviour of reinforcement learning (RL) algorithms is best understood in completely
observable, finite state-and action-space, discrete-time controlled Markov-chains. Robot …

Recently researchers have introduced methods to develop reusable knowledge in
reinforcement learning (RL). In this paper, we define simple principles to combine skills in …