Related papers: Force Field Generalization and the Internal Repres…

Adapting upper-limb impedance (i.e., stiffness, damping, inertia) is essential for humans interacting with dynamic environments for executing grasping or manipulation tasks. On the other hand, control methods designed for state-of-the-art…

This paper presents an approach for learning invariant features for object affordance understanding. One of the major problems for a robotic agent acquiring a deeper understanding of affordances is finding sensory-grounded semantics. Being…

While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state…

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How does such…

In humans, body segments' position and movement can be estimated from multiple senses such as vision and proprioception. It has been suggested that vision and proprioception can influence each other and that upper-limb proprioception is…

Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where…

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement…

Transformers serve as the foundational architecture for many successful large-scale models, demonstrating the ability to overfit the training data while maintaining strong generalization on unseen data, a phenomenon known as benign…

Predicting an agent's future trajectory is a challenging task given the complicated stimuli (environmental/inertial/social) of motion. Prior works learn individual stimulus from different modules and fuse the representations in an…

In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments, rather than merely as predictors of predefined labels. When the measurement function is learned from data, the…

Many manipulation tasks require robots to interact with unknown environments. In such applications, the ability to adapt the impedance according to different task phases and environment constraints is crucial for safety and performance.…

In searching for a generalizable representation of temporally extended tasks, we spot two necessary constituents: the utility needs to be non-Markovian to transfer temporal relations invariant to a probability shift, the utility also needs…

Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are trained in a fixed environment, such as a single level in a…

Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a generalizable policy, as the testing environment may differ from…

In order to determine indirectly the generalized forces applied on the gearbox, two approaches are tested, one is a numerical method, the other is experimental. For the numerical method, the vibration response of the gearbox can be…

Transfer learning is a useful technique for achieving improved performance and reducing training costs by leveraging the knowledge gained from source tasks and applying it to target tasks. Assessing the effectiveness of transfer learning…

Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexplored. We show that embeddings are central to grokking:…

Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its training distribution using quantities available prior to test-time evaluation. Building on the…

Can we endow visuomotor robots with generalization capabilities to operate in diverse open-world scenarios? In this paper, we propose \textbf{Maniwhere}, a generalizable framework tailored for visual reinforcement learning, enabling the…