Related papers: Pre-trained Visual Representations Generalize Wher…
Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given…
Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data…
Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…
Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…
The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…
Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…
We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. Our framework trains deep visuomotor…
Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…
Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…
Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited…
In this paper, we examine the effectiveness of pre-training for visuo-motor control tasks. We revisit a simple Learning-from-Scratch (LfS) baseline that incorporates data augmentation and a shallow ConvNet, and find that this baseline is…
Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and…
Recent advances in supervised learning and reinforcement learning have provided new opportunities to apply related methodologies to automated driving. However, there are still challenges to achieve automated driving maneuvers in dynamically…
Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual…
Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing,…
Vision-Language Models (VLMs) have recently demonstrated strong capabilities in mapping multimodal observations to robot behaviors. However, most current approaches rely on end-to-end visuomotor policies that remain opaque and difficult to…
Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…
Deep Reinforcement Learning (DRL) holds significant promise for achieving human-like Autonomous Vehicle (AV) capabilities, but suffers from low sample efficiency and challenges in reward design. Model-Based Reinforcement Learning (MBRL)…
Model-based reinforcement learning (RL) algorithms allow us to combine model-generated data with those collected from interaction with the real system in order to alleviate the data efficiency problem in RL. However, designing such…
Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement…