Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this paper, we develop a novel experience-driven approach that can learn to well control a communication network from its own experience rather than an accurate mathematical model, just as a human learns a new skill (such as driving, swimming, etc). Specifically...

In this work, we used time-resolved imaging to study the dynamics of the laser-induced forward transfer (LIFT) process of a silver nanoparticle (NP) ink (NP size: 30–50 nm). LIFT is a versatile direct write technique in which a variety of functional materials can be transferred from a donor substrate to a receiving substrate with high spatial resolution. Two different LIFT configurations were e...

The derailed (drl) gene encodes a receptor tyrosine kinase (RTK) that governs aspects of axon guidance and muscle-epidermal interactions in the Drosophila embryo. To determine the types of neurons that express drl, we have examined a series of drl promoter fusions to axon-targeted reporters. We have identified enhancers that drive reporter expression in four distinct subtypes of embryonic neuro...

Traffic Safety Administration, in the interest of information exchange. The opinions, findings, and conclusions expressed in this publication are those of the authors and not necessarily those of the Department of Transportation or the National Highway Traffic Safety Administration. The United States Government assumes no liability for its contents or use thereof. If trade names, manufacturers'...

We propose a novel framework for Deep Reinforcement Learning (DRL) in modular robotics using traditional robotic tools that extend state-of-the-art DRL implementations and provide an end-to-end approach which trains a robot directly from joint states. Moreover, we present a novel technique to transfer these DLR methods into the real robot, aiming to close the simulation-reality gap. We demonstr...

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video data is substantially distinct from what a human ...

In ‘Comments on Theeuwes and Riemersma’s Revisit of Daytime Running Lights’ Williams and Farmer ( 1996) comment on a paper we published in Accident Analysis and Prevention. In this paper we show that the original claim by Andersson and Nilsson ( 198 1) that the nationwide implementation of Daytime Running Lights (DRL) in Sweden resulted in a reduction of multiple daytime accidents was not warra...

BACKGROUND Currently available tools for identifying individuals at high risk of type 2 diabetes can be invasive, costly and time consuming. This study aims to develop and validate a self-assessment tool for identifying individuals at high risk of type 2 diabetes in the Chinese general population. METHODS A cross-sectional survey was conducted from 2000 to 2001 in a nationally representative ...

We introduce the idea of Data Readiness Level (DRL) to measure the relative richness of data to answer specific questions often encountered by data scientists. We first approach the problem in its full generality explaining its desired mathematical properties and applications and then we propose and study two DRL metrics. Specifically, we define DRL as a function of at least four properties of ...