Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's
knowledge about the underlying dynamics of the environment, enabling learning a world …

The visual world provides an abundance of information, but many input pixels received by
agents often contain distracting stimuli. Autonomous agents need the ability to distinguish …

Abstract Model-based reinforcement learning (MBRL) is a promising route to sample-
efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL …

Electronic healthcare records are vital for patient safety as they document conditions, plans,
and procedures in both free text and medical codes. Language models have significantly …

Model-based offline reinforcement Learning (RL) is a promising approach that leverages
existing data effectively in many real-world applications, especially those involving high …

Trajectory prediction models in autonomous driving are vulnerable to perturbations from non-
causal agents whose actions should not affect the ego-agent's behavior. Such perturbations …

At the core of both successful generative and self-supervised representation learning
models there is a reconstruction objective that incorporates some form of image corruption …

Masked prediction has emerged as a promising pretraining paradigm in offline
reinforcement learning (RL) due to its versatile masking schemes, enabling flexible …

Humans excel at isolating relevant information from noisy data to predict the behavior of
dynamic systems, effectively disregarding non-informative, temporally-correlated noise. In …

Visual offline RL aims to learn an optimal policy for visual domains, solely from the pre-
collected dataset comprised of actions taken on visual observations. Prior works on visual …