Recent advances in zero-shot image recognition suggest that vision-language models learn
generic visual representations with a high degree of semantic information that may be …

This review addresses the problem of learning abstract representations of the measurement
data in the context of Deep Reinforcement Learning (DRL). While the data are often …

We investigate whether self-supervised learning (SSL) can improve online reinforcement
learning (RL) from pixels. We extend the contrastive reinforcement learning framework (eg …

Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …

Diffusion models have been adopted for behavioral cloning in a sequence modeling
fashion, benefiting from their exceptional capabilities in modeling complex data distributions …

Vision-based robot policy learning, which maps visual inputs to actions, necessitates a
holistic understanding of diverse visual tasks beyond single-task needs like classification or …

Abstract Visual Reinforcement Learning (RL) agents trained on limited views face significant
challenges in generalizing their learned abilities to unseen views. This inherent difficulty is …

With the fast improvement of machine learning, reinforcement learning (RL) has been used
to automate human tasks in different areas. However, training such agents is difficult and …

Reinforcement Learning (RL) can be considered as a sequence modeling task: given a
sequence of past state-action-reward experiences, an agent predicts a sequence of next …

Humans are remarkably flexible in understanding viewpoint changes due to visual cortex
supporting the perception of 3D structure. In contrast, most of the computer vision models …