Training novice users to operate an excavator for learning different skills requires the
presence of expert teachers. Considering the complexity of the problem, it is comparatively …

We explore beyond existing work in learning from demonstration by asking the
question:“Can robots learn to guide?”, that is, can a robot autonomously learn an …

In this paper, we propose a control algorithm based on reinforcement learning, employing
independent rewards for each joint to control excavators in a 3D space. The aim of this …

To keep up with the world's increasing complexity, we need ever-more sophisticated
computational models that can help to make wiser decisions and accurately predict potential …

The pre-train and fine-tune paradigm in machine learning has had dramatic success in a
wide range of domains because the use of existing data or pre-trained models on the …

One of the key challenges in implementing reinforcement learning methods for real-world
robotic applications is the design of a suitable reward function. In field robotics, the absence …

Learning from demonstration algorithms, such as Inverse Reinforcement Learning, aim to
provide a natural mechanism for programming robots, but can often require a prohibitive …

Physical interactions can often help reveal information that is not readily apparent. For
example, we may tug at a table leg to evaluate whether it is built well, or turn a water bottle …

The learning efficiency and generalization ability of an intelligent agent can be greatly
improved by utilizing a useful set of skills. However, the design of robot skills can often be …

We propose a scheme for training a computerized agent to perform complex human tasks
such as highway steering. The scheme resembles natural teaching-learning processes used …