Zobrazeno 1 - 10
of 138
pro vyhledávání: '"Fullana, Miguel A."'
Autor:
Agorio, Leopoldo, Van Alen, Sean, Calvo-Fullana, Miguel, Paternain, Santiago, Bazerque, Juan Andres
Publikováno v:
Proceedings of Machine Learning Research vol 242 1 12, 2024. 6th Annual Conference on Learning for Dynamics and Control
We address the conflicting requirements of a multi-agent assignment problem through constrained reinforcement learning, emphasizing the inadequacy of standard regularization techniques for this purpose. Instead, we recur to a state augmentation appro
Externí odkaz:
http://arxiv.org/abs/2406.01782
Autor:
Calvo-Fullana, Miguel, Gerasimenko, Mikhail, Mox, Daniel, Agorio, Leopoldo, del Castillo, Mariana, Kumar, Vijay, Ribeiro, Alejandro, Bazerque, Juan Andres
Despite the prevalence of wireless connectivity in urban areas around the globe, there remain numerous and diverse situations where connectivity is insufficient or unavailable. To address this, we introduce mobile wireless infrastructure on demand, a
Externí odkaz:
http://arxiv.org/abs/2306.08737
In this paper, we study the problem of distributed estimation with an emphasis on communication-efficiency. The proposed algorithm is based on a windowed maximum a posteriori (MAP) estimation problem, wherein each agent in the network locally compute
Externí odkaz:
http://arxiv.org/abs/2211.11038
Multi-task learning aims to acquire a set of functions, either regressors or classifiers, that perform well for diverse tasks. At its core, the idea behind multi-task learning is to exploit the intrinsic similarity across data sources to aid in the l
Externí odkaz:
http://arxiv.org/abs/2210.15573
This work presents a distributed estimation algorithm that efficiently uses the available communication resources. The approach is based on Bayesian filtering that is distributed across a network by using the logarithmic opinion pool operator. Commun
Externí odkaz:
http://arxiv.org/abs/2204.00474
Autor:
Tian, Yulun, Bedi, Amrit Singh, Koppel, Alec, Calvo-Fullana, Miguel, Rosen, David M., How, Jonathan P.
We present the first distributed optimization algorithm with lazy communication for collaborative geometric estimation, the backbone of modern collaborative simultaneous localization and mapping (SLAM) and structure-from-motion (SfM) applications. Ou
Externí odkaz:
http://arxiv.org/abs/2203.00851
Though learning has become a core component of modern information processing, there is now ample evidence that it can lead to biased, unsafe, and prejudiced systems. The need to impose requirements on learning is therefore paramount, especially as it
Externí odkaz:
http://arxiv.org/abs/2103.05134
Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions. However, the
Externí odkaz:
http://arxiv.org/abs/2102.12585
A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be induced by a
Externí odkaz:
http://arxiv.org/abs/2102.11941
Autor:
Calvo-Fullana, Miguel, Mox, Daniel, Pyattaev, Alexander, Fink, Jonathan, Kumar, Vijay, Ribeiro, Alejandro
Multi-agent systems play an important role in modern robotics. Due to the nature of these systems, coordination among agents via communication is frequently necessary. Indeed, Perception-Action-Communication (PAC) loops, or Perception-Action loops cl
Externí odkaz:
http://arxiv.org/abs/2101.10113