Related papers: Evolving generalist controllers to handle a wide r…

Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor…

Transformer-based models excel in various tasks but their generalization capabilities, especially in arithmetic reasoning, remain incompletely understood. Arithmetic tasks provide a controlled framework to explore these capabilities, yet…

In evolutionary robotics, jointly optimising the design and the controller of robots is a challenging task due to the huge complexity of the solution space formed by the possible combinations of body and controller. We focus on the…

That shared features between train and test data are required for generalisation in artificial neural networks has been a common assumption of both proponents and critics of these models. Here, we show that convolutional architectures avoid…

Regularization is commonly used for alleviating overfitting in machine learning. For convolutional neural networks (CNNs), regularization methods, such as DropBlock and Shake-Shake, have illustrated the improvement in the generalization…

This paper proposes an adaptive modular geometric control framework for robotic manipulators. The proposed methodology decomposes the overall manipulator dynamics into individual modules, enabling the design of local geometric control laws…

Evolution sculpts both the body plans and nervous systems of agents together over time. In contrast, in AI and robotics, a robot's body plan is usually designed by hand, and control policies are then optimized for that fixed design. The…

The idea of symbolic controllers tries to bridge the gap between the top-down manual design of the controller architecture, as advocated in Brooks' subsumption architecture, and the bottom-up designer-free approach that is now standard…

Though recent studies have made significant progress in morph attack detection by virtue of deep neural networks, they often fail to generalize well to unseen morph attacks. With numerous morph attacks emerging frequently, generalizable…

Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies. However, most current approaches use minor variants of a Graph Convolutional Network (GCN), which applies…

Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramount importance to guarantee a successful deployment. Optimal…

Humans and animals developed a sophisticated motor control apparatus and there is much evidence that it has a modular structure. The modularity offers a range of benefits, e.g. ability to learn dissociable motion styles without interference…

Soft robotics has advanced rapidly, yet its control methods remain fragmented: different morphologies and actuation schemes still require task-specific controllers, hindering theoretical integration and large-scale deployment. A generic…

Graph convolutional neural networks (GCNs) generalize tradition convolutional neural networks (CNNs) from low-dimensional regular graphs (e.g., image) to high dimensional irregular graphs (e.g., text documents on word embeddings). Due to…

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural…

To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent successes have come from methods that pre-specify the types of…

Soft robotics are increasingly favoured in specific applications such as healthcare, due to their adaptability, which stems from the non-linear properties of their building materials. However, these properties also pose significant…

Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain…

Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge. Recent machine learning breakthroughs have heralded policies that master individual skills like reaching, object…

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations from structured data. Despite their growing popularity and success across various applications, GNNs encounter several challenges that limit their…