Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

Data augmentation, the artificial creation of training data for machine learning by
transformations, is a widely studied research field across machine learning disciplines …

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain
without using any source data. Existing works mainly consider the case where the target …

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

Isaac Gym offers a high performance learning platform to train policies for wide variety of
robotics tasks directly on GPU. Both physics simulation and the neural network policy …

Animals are capable of precise and agile locomotion using vision. Replicating this ability
has been a long-standing goal in robotics. The traditional approach has been to decompose …

We investigated whether deep reinforcement learning (deep RL) is able to synthesize
sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Executing safe and precise flight maneuvers in dynamic high-speed winds is important for
the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the …

Successful real-world deployment of legged robots would require them to adapt in real-time
to unseen scenarios like changing terrains, changing payloads, wear and tear. This paper …