In reinforcement learning (RL), it is easier to solve a task if given a good representation.
While deep RL should automatically acquire such good representations, prior work often …

Unsupervised pre-training has recently become the bedrock for computer vision and natural
language processing. In reinforcement learning (RL), goal-conditioned RL can potentially …

Leveraging the compositional nature of our world to expedite learning and facilitate
generalization is a hallmark of human perception. In machine learning, on the other hand …

Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully
offline datasets. In addition to being conservative within the dataset, the generalization …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Machine learning systems, especially with overparameterized deep neural networks, can
generalize to novel test instances drawn from the same distribution as the training data …

Unmanned aerial vehicles, and special multirotor drones, have shown great relevance in a
plethora of missions that require high affordance, field of view, and precision. Their limited …

For zero-shot transfer in reinforcement learning where the reward function varies between
different tasks, the successor features framework has been one of the popular approaches …

Goal-conditioned reinforcement learning (GCRL) has a wide range of potential real-world
applications, including manipulation and navigation problems in robotics. Especially in such …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …