%A Besson, Lilian %A Bonnefoi, Rémi %A Moy, Christophe %D 2021 %T GNU Radio Implementation and Demonstration of MALIN: “Multi-Arm bandits Learning for Internet-of-things Networks” %K %X We implement 1 an IoT network the following way: one gateway, one or several intelligent (learning) ob jects, embedding the proposed solution, and a traf fic generator that emulates radio interferences from many other objects. Intelligent objects commu nicate with the gateway with a wireless ALOHA- based protocol with no specific overhead for learn ing needs. We model the network access as a dis crete sequential decision making, and using the framework and algorithms from Multi-Armed Ban dit (MAB) learning, we show that intelligent ob jects can improve their access to the network by us ing load complexity and decentralized algorithms, such as UCB and Thompson Sampling. %U https://pubs.gnuradio.org/index.php/grcon/article/view/79 %J Proceedings of the GNU Radio Conference %0 Journal Article %V 1 %N 1 %8 2021-01-02