Reinforcement learning for demand response: A review of algorithms and modeling techniques

JR Vázquez-Canteli, Z Nagy - Applied energy, 2019 - Elsevier
Buildings account for about 40% of the global energy consumption. Renewable energy
resources are one possibility to mitigate the dependence of residential buildings on the …

Joint status sampling and updating for minimizing age of information in the Internet of Things

B Zhou, W Saad - IEEE Transactions on Communications, 2019 - ieeexplore.ieee.org
The effective operation of time-critical Internet of things (IoT) applications requires real-time
reporting of fresh status information of underlying physical processes. In this paper, a real …

The value of abstraction

MK Ho, D Abel, TL Griffiths, ML Littman - Current opinion in behavioral …, 2019 - Elsevier
In spite of bounds on space, time, and data, people are able to make good decisions in
complex scenarios. What enables us to do so? And what might equip artificial systems to do …

Optimal downlink–uplink scheduling of wireless networked control for industrial IoT

K Huang, W Liu, Y Li, B Vucetic… - IEEE Internet of Things …, 2019 - ieeexplore.ieee.org
This article considers a wireless networked control system (WNCS) consisting of a dynamic
system to be controlled (ie, a plant), a sensor, an actuator, and a remote controller for …

Finding options that minimize planning time

Y Jinnai, D Abel, D Hershkowitz… - International …, 2019 - proceedings.mlr.press
We formalize the problem of selecting the optimal set of options for planning as that of
computing the smallest set of options so that planning converges in less than a given …

Optimal power allocation for wireless sensor powered by dedicated RF energy source

Q Li, J Gao, H Liang, L Zhao… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
This paper studies a wireless-powered sensor network, where a sensor harvests energy
from a dedicated radio-frequency (RF) energy source and transmits information to an …

The value function polytope in reinforcement learning

R Dadashi, AA Taiga, N Le Roux… - International …, 2019 - proceedings.mlr.press
We establish geometric and topological properties of the space of value functions in finite
state-action Markov decision processes. Our main contribution is the characterization of the …

Formal quality of service assurances, ranking and verification of cloud deployment options with a probabilistic model checking method

P Kochovski, PD Drobintsev, V Stankovski - Information and Software …, 2019 - Elsevier
Context: Existing software workbenches allow for the deployment of cloud applications
across a variety of Infrastructure-as-a-Service (IaaS) providers. The expected workload …

Adversarial imitation learning from incomplete demonstrations

M Sun, X Ma - arXiv preprint arXiv:1905.12310, 2019 - arxiv.org
Imitation learning targets deriving a mapping from states to actions, aka policy, from expert
demonstrations. Existing methods for imitation learning typically require any actions in the …

What makes long‐term monitoring convenient? A parametric analysis of value of information in infrastructure maintenance

S Li, M Pozzi - Structural Control and Health Monitoring, 2019 - Wiley Online Library
Information collected by monitoring systems can provide a significant economic benefit to
the operation and maintenance of infrastructure components only under specific conditions …