With the fast improvement of machine learning, reinforcement learning (RL) has been used
to automate human tasks in different areas. However, training such agents is difficult and …

Learning from demonstration is an approach that allows users to personalize a robot's tasks.
While demonstrations often focus on conveying the robot's motion or task plans, they can …

Inverse reinforcement learning is a paradigm motivated by the goal of learning general
reward functions from demonstrated behaviours. Yet the notion of generality for learnt costs …

Sequential modelling of high-dimensional data is an important problem that appears in
many domains including model-based reinforcement learning and dynamics identification …

Some actions must be executed in different ways depending on the context. For example,
wiping away marker requires vigorous force while wiping away almonds requires more …

Out-of-distribution (OOD) detection, ie, finding test samples derived from a different
distribution than the training set, as well as reasoning about such samples (OOD reasoning) …

We present Perceive-Represent-Generate (PRG), a novel three-stage framework that maps
perceptual information of different modalities (eg, visual or sound), corresponding to a series …

An important feature of human sensorimotor skill is our ability to learn to reuse them across
different environmental contexts, in part due to our understanding of attributes of variability in …

In complex teaching scenarios it can be difficult for teachers to exhaustively express all
information a learner requires to master a task. However, the teacher, who will have …