Given the continually rising frequency of cyberattacks, the adoption of artificial intelligence
methods, particularly Machine Learning (ML), Deep Learning (DL), and Reinforcement …

Model-based reinforcement learning methods often use learning only for the purpose of
estimating an approximate dynamics model, offloading the rest of the decision-making work …

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 …

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient
robot learning from visual observations. Yet the current approaches typically train a single …

Recent unsupervised pre-training methods have shown to be effective on language and
vision domains by learning useful representations for multiple downstream tasks. In this …

Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still
impose a major challenge in offline robot control. While a number of prior methods aimed to …

Visual model-based RL methods typically encode image observations into low-dimensional
representations in a manner that does not eliminate redundant information. This leaves them …

Learning representations in the joint domain of vision and touch can improve manipulation
dexterity, robustness, and sample-complexity by exploiting mutual information and …

Off-policy evaluation (OPE) is important for closing the gap between offline training and
evaluation of reinforcement learning (RL), by estimating performance and/or rank of target …

Dropped into an unknown environment, what should an agent do to quickly learn about the
environment and how to accomplish diverse tasks within it? We address this question within …