Related papers: Zero-Shot Action Generalization with Limited Obser…
Capturing latent variations ("contexts") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control problem and formally characterize two properties and their…
Articulated object manipulation poses a unique challenge compared to rigid object manipulation as the object itself represents a dynamic environment. In this work, we present a novel RL-based pipeline equipped with variable impedance…
The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…
Pre-training large models on vast amounts of web data has proven to be an effective approach for obtaining powerful, general models in domains such as language and vision. However, this paradigm has not yet taken hold in reinforcement…
In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL…
Aligning a lens system relative to an imager is a critical challenge in camera manufacturing. While optimal alignment can be mathematically computed under ideal conditions, real-world deviations caused by manufacturing tolerances often…
A generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabilities. Consequently, they are often limited to single…
Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train…
Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing verbalized and interpretable representation can significantly…
Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to…
Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current…
Learning real-world robotic manipulation is challenging, particularly when limited demonstrations are available. Existing methods for few-shot manipulation often rely on simulation-augmented data or pre-built modules like grasping and pose…
Deep reinforcement learning has been applied to solve a variety of control problems in isolation. However, the learned latent representations cannot be optimally reused for other analogous tasks and/or control systems without additional…
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain generalization (DG), to separately address the issues of…
Robots still lag behind humans in their ability to generalize from limited experience, particularly when transferring learned behaviors to long-horizon tasks in unseen environments. We present the first method that enables robots to…
Vision-Language-Action (VLA) models have shown remarkable achievements, driven by the rich implicit knowledge of their vision-language components. However, achieving generalist robotic agents demands precise grounding into physical…
Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are often restricted by the…
Reinforcement learning (RL) allows to solve complex tasks such as Go often with a stronger performance than humans. However, the learned behaviors are usually fixed to specific tasks and unable to adapt to different contexts. Here we…
Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…
Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that…