While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

In many sequential decision-making problems (eg, robotics control, game playing,
sequential prediction), human or expert data is available containing useful information about …

Learning from demonstration, or imitation learning, is the process of learning to act in an
environment from examples provided by a teacher. Inverse reinforcement learning (IRL) is a …

Abstract Setting up a well-designed reward function has been challenging for many
reinforcement learning applications. Preference-based reinforcement learning (PbRL) …

How to extract as much learning signal from each trajectory data has been a key problem in
reinforcement learning (RL), where sample inefficiency has posed serious challenges for …

We present Neural A*, a novel data-driven search method for path planning problems.
Despite the recent increasing attention to data-driven path planning, machine learning …

Motivated by the success of ensembles for uncertainty estimation in supervised learning, we
take a renewed look at how ensembles of $ Q $-functions can be leveraged as the primary …

Theory of mind (ToM) is the psychological construct by which we model another's internal
mental states. Through ToM, we adjust our own behaviour to best suit a social context, and …

As AI systems are integrated into high stakes social domains, researchers now examine how
to design and operate them in a safe and ethical manner. However, the criteria for identifying …

Learning new skills by observing humans' behaviors is an essential capability of AI. In this
work, we leverage instructional videos to study humans' decision-making processes …