Related papers: Learning to crawl: Benefits and limits of centrali…

State-of-the-art distributed algorithms for reinforcement learning rely on multiple independent agents, which simultaneously learn in parallel environments while asynchronously updating a common, shared policy. Moreover, decentralized…

In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain neurons and synapses self-adjust based on local information. Contrastive learning algorithms have recently been…

A linear flow control strategy designed for weak disturbances may not remain effective in sequences of strong disturbances due to nonlinear interactions, but it is sensible to leverage it for developing a better strategy. In the present…

We present a framework for learning visually-guided quadruped locomotion by integrating exteroceptive sensing and central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework.…

This work explores the potential of using differentiable simulation for learning quadruped locomotion. Differentiable simulation promises fast convergence and stable training by computing low-variance first-order gradients using robot…

Distributed learning techniques such as federated learning have enabled multiple workers to train machine learning models together to reduce the overall training time. However, current distributed training algorithms (centralized or…

Achieving controlled jumping behaviour for a quadruped robot is a challenging task, especially when introducing passive compliance in mechanical design. This study addresses this challenge via imitation-based deep reinforcement learning…

Federated Learning is a framework that jointly trains a model \textit{with} complete knowledge on a remotely placed centralized server, but \textit{without} the requirement of accessing the data stored in distributed machines. Some work…

Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image…

We present an architecture where a feedback controller derived on an approximate model of the environment assists the learning process to enhance its data efficiency. This architecture, which we term as Control-Tutored Q-learning (CTQL), is…

Many cloud applications are migrated from the monolithic model to a microservices framework in which hundreds of loosely-coupled microservices run concurrently, with significant benefits in terms of scalability, rapid development,…

Learning natural and diverse behaviors from human motion datasets remains challenging in physics-based character control. Existing conditional adversarial models often suffer from tight and biased embedding distributions where embeddings…

Taking inspiration from the crawling motion of biological cells on a substrate, we consider a physical model of self-propulsion where the spatio-temporal driving can involve both, a mechanical actuation by active force couples, and a…

A low-rank transformation learning framework for subspace clustering and classification is here proposed. Many high-dimensional data, such as face images and motion sequences, approximately lie in a union of low-dimensional subspaces. The…

Federated Learning (FL) has emerged as a transformative approach for enabling distributed machine learning while preserving user privacy, yet it faces challenges like communication inefficiencies and reliance on centralized infrastructures,…

Decentralized optimization enables multiple devices to learn a global machine learning model while each individual device only has access to its local dataset. By avoiding the need for training data to leave individual users' devices, it…

Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in recent years. Compressing these models not only reduces storage requirements, making deployment to edge devices feasible, but also accelerates inference,…

Compliant robots can be more versatile than traditional robots, but their control is more complex. The dynamics of compliant bodies can however be turned into an advantage using the physical reservoir computing frame-work. By feeding sensor…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms by means of a control strategy with limited knowledge of the system model. By tutoring the learning process, the…

We study a model of cell motility where the condition of optimal trade-off between performance and metabolic cost can be made precise. In this model a steadily crawling fragment is represented by a layer of active gel placed on a frictional…