Results 21 to 30 of about 56 (54)
Multi‐Objective Reinforcement Learning for Automated Resilient Cyber Defence
Autonomous Cyber Defence agents were trained using multi‐objective reinforcement learning to defend a computer network against red‐agent attack, trading off network security and service availability. A Pareto Front was established (lower left), which shows the trade off between accessing network services (green) and defending against compromised ...
Ross O'Driscoll +3 more
wiley +1 more source
Mean‐field limit of non‐exchangeable systems
Abstract This paper deals with the derivation of the mean‐field limit for multi‐agent systems on a large class of sparse graphs. More specifically, the case of non‐exchangeable multi‐agent systems consisting of non‐identical agents is addressed. The analysis does not only involve PDEs and stochastic analysis but also graph theory through a new concept ...
Pierre‐Emmanuel Jabin +2 more
wiley +1 more source
We introduce a fully distributed framework that leverages belief‐desire‐intention extended (BDIx) agents on user devices to perform dynamic clustering and access‐point selection in a cell‐free 6G network, using both classical and deep‐learning methods for deterministic, scalable AP grouping.
Iakovos Ioannou +5 more
wiley +1 more source
On the smooth Whitney fibering conjecture
Abstract We improve upon the first Thom–Mather isotopy theorem for Whitney stratified sets. In particular, for the more general Bekka stratified sets we show that there is a local foliated structure with continuously varying tangent spaces, thus proving the smooth version of the Whitney fibering conjecture.
C. Murolo +2 more
wiley +1 more source
A natural adaptive process for collective decision‐making
Consider an urn filled with balls, each labeled with one of several possible collective decisions. Now let a random voter draw two balls from the urn and pick her more preferred as the collective decision. Relabel the losing ball with the collective decision, put both balls back into the urn, and repeat.
Florian Brandl, Felix Brandt
wiley +1 more source
Control strategy for biopharmaceutical production by model predictive control
Abstract The biopharmaceutical industry is rapidly advancing, driven by the need for cutting‐edge technologies to meet the growing demand for life‐saving treatments. In this context, Model Predictive Control (MPC) has emerged as a promising solution to address the complexity of modern biopharmaceutical production processes.
Touraj Eslami, Alois Jungbauer
wiley +1 more source
Hiding the elephant: The tragedy of COVID policy and its economist apologists
Abstract In 2020 and 2021, the world witnessed policies that caused enormous net damage to most countries. We demonstrate the usefulness of the new WELLBY currency in gauging the costs and benefits of COVID policies and review the contributions of Australian economists to the scholarly and public debates about these policies. Our analysis documents the
Gigi Foster, Paul Frijters
wiley +1 more source
Abstract To plan the postal deliveries of our industry partner DHL Group (DHL), the single truck and trailer routing problem with satellite depots (STTRPSD) is solved to optimize mail carriers routes. In this application context, instances feature a high number of customers and satellites, and they are based on real street networks.
Rossana Cavagnini +2 more
wiley +1 more source
Abstract Supplement HIV Glasgow 10–13 November 2024, Glasgow, UK/Virtual
Journal of the International AIDS Society, Volume 27, Issue S6, November 2024.
wiley +1 more source
Fast large-tip-angle multidimensional and parallel RF pulse design in MRI. [PDF]
Grissom WA +4 more
europepmc +1 more source

