QMR: Q-learning based Multi-objective optimization Routing protocol

In this work I've implemented the Q-learning based protocol proposed in QMR:Q-learning based Multi-objective optimization Routing protocol for Flying Ad Hoc Networks by Liu et al. using DroNet, a Python-based simulator for experimenting routing algorithms and mobility models on unmanned aerial vehicle networks, created by Andrea Coletta and Matteo Prata, both PhD students at Sapienza University of Rome. If you want to learn how to use the simulator, go to the original DroNet implementation and follow the README. I would like to clarify that the simulator is very simplified w.r.o. a realistic simulation, so the results obtained in this repo can be very different from the paper results.