Perceptual grouping in contrastive vision-language models
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 …
generic visual representations with a high degree of semantic information that may be …
Unsupervised representation learning in deep reinforcement learning: A review
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 …
data in the context of Deep Reinforcement Learning (DRL). While the data are often …
Does self-supervised learning really improve reinforcement learning from pixels?
We investigate whether self-supervised learning (SSL) can improve online reinforcement
learning (RL) from pixels. We extend the contrastive reinforcement learning framework (eg …
learning (RL) from pixels. We extend the contrastive reinforcement learning framework (eg …
Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions
Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …
particularly in generating texts, images, and videos using models trained from offline data …
Crossway diffusion: Improving diffusion-based visuomotor policy via self-supervised learning
Diffusion models have been adopted for behavioral cloning in a sequence modeling
fashion, benefiting from their exceptional capabilities in modeling complex data distributions …
fashion, benefiting from their exceptional capabilities in modeling complex data distributions …
Theia: Distilling diverse vision foundation models for robot learning
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 …
holistic understanding of diverse visual tasks beyond single-task needs like classification or …
Movie: Visual model-based policy adaptation for view generalization
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 …
challenges in generalizing their learned abilities to unseen views. This inherent difficulty is …
[HTML][HTML] A survey of demonstration learning
A Correia, LA Alexandre - Robotics and Autonomous Systems, 2024 - Elsevier
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 …
to automate human tasks in different areas. However, training such agents is difficult and …
Starformer: Transformer with state-action-reward representations for visual reinforcement learning
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 …
sequence of past state-action-reward experiences, an agent predicts a sequence of next …
Learning viewpoint-agnostic visual representations by recovering tokens in 3d space
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 …
supporting the perception of 3D structure. In contrast, most of the computer vision models …