# GNU Radio Implementation of MALIN: "Multi-Armed bandits Learning for Internet-of-things Networks"

## TL;DR

This paper demonstrates how multi-armed bandit algorithms can be implemented in GNU Radio to enable intelligent IoT devices to learn optimal network access strategies in interference-prone environments, with minimal overhead.

## Contribution

It introduces a GNU Radio implementation of MAB algorithms for IoT networks, enabling decentralized learning-based access without network modifications.

## Key findings

- Intelligent objects improve network access using UCB1 and Thompson Sampling.
- The solution is easily integrable into LoRaWAN devices.
- Decentralized learning enhances network efficiency in interference scenarios.

## Abstract

We implement an IoT network the following way: one gateway, one or several intelligent (i.e., learning) objects, embedding the proposed solution, and a traffic generator that emulates radio interferences from many other objects. Intelligent objects communicate with the gateway with a wireless ALOHA-based protocol, which does not require any specific overhead for the learning. We model the network access as a discrete sequential decision making problem, and using the framework and algorithms from Multi-Armed Bandit (MAB) learning, we show that intelligent objects can improve their access to the network by using low complexity and decentralized algorithms, such as UCB1 and Thompson Sampling. This solution could be added in a straightforward and costless manner in LoRaWAN networks, just by adding this feature in some or all the devices, without any modification on the network side.