Policy Learning approaches are among the best suited methods for high-dimensional, continuous control systems such as anthropomorphic robot arms and humanoid robots. In this paper, we show two contributions: firstly, we show a unified perspective which allows us to derive several policy learning algorithms from a common point of view, i.e, policy gradient algorithms, naturalgradient algorithms ...

This paper presents a new reinforcement learning algorithm that enables collaborative learning between a robot and a human. The algorithm which is based on the Q(λ) approach expedites the learning process by taking advantage of human intelligence and expertise. The algorithm denoted as CQ(λ) provides the robot with self awareness to adaptively switch its collaboration level from autonomous (sel...

Despite the advancement of research and development on multi-robot teams, a key challenge still remains as to how to develop effective mechanisms that enable the robots to autonomously generate, adapt, and enhance team behaviours while improving their individual performance simultaneously. After a literature review of various multi-agent learning approaches, the two most promising learning para...

This paper studies the essential dynamical structure that arises in two different classes of learning of the sensory-based navigation, namely 3kill·ba3ed learning and model-ba3ed learning. In 3kill·ba3ed learning a robot learns navigational skills for a fixed navigational task such as homing, while in modelba3ed learning a robot learns a model of the environment, then conducts planning on the m...

This paper illustrated an application of Locally Weighted Projection Regression to a complex robot learning task. The O(n) update complexity of LWPR, together with its statistically sound dimensionality reduction and learning rules allowed a reliable and successful real-time implementation of the algorithm on an actual anthropomorphic robot. From the viewpoint of learning control, these results...

One of the main goals of autonomous robotics is to have a robot learning and adapting to a dynamically changing environment over a long operating period. In this paper we present a proposal for such continual learning, by illustrating some of the key issues we think have to be addressed in order to have a robot learning in a constructive way. We describe an experiment where a mobile robot learn...