Energy Aware Deep Reinforcement Learning Scheduling for Sensors Correlated in Time and Space

no code implementations • 19 Nov 2020 • Jernej Hribar, Andrei Marinescu, Alessandro Chiumento, Luiz A. DaSilva

The proposed mechanism is capable of determining the frequency with which sensors should transmit their updates, to ensure accurate collection of observations, while simultaneously considering the energy available.

reinforcement-learning Reinforcement Learning (RL) +1

Decentralised Multi-Agent Reinforcement Learning for Dynamic and Uncertain Environments

no code implementations • 16 Sep 2014 • Andrei Marinescu, Ivana Dusparic, Adam Taylor, Vinny Cahill, Siobhán Clarke

In this paper we propose P-MARL, a decentralised MARL algorithm enhanced by a prediction mechanism that provides accurate information regarding up-coming changes in the environment.

Multiagent Systems