A Reinforcement Learning Environment for Multi-Service UAV-enabled Wireless Systems

TL;DR

This paper introduces a flexible OpenAI Gym environment for training and benchmarking reinforcement learning policies in multi-service UAV-enabled wireless systems, supporting various applications like connectivity, edge computing, and data gathering.

Contribution

It presents a novel, extensible simulation environment for autonomous UAV systems that enables policy development, evaluation, and comparison across diverse multi-service scenarios.

Findings

Policies outperform simple baselines in various tasks

Environment facilitates benchmarking of different approaches

Guidelines for adopting RL in UAV multi-service applications

Abstract

We design a multi-purpose environment for autonomous UAVs offering different communication services in a variety of application contexts (e.g., wireless mobile connectivity services, edge computing, data gathering). We develop the environment, based on OpenAI Gym framework, in order to simulate different characteristics of real operational environments and we adopt the Reinforcement Learning to generate policies that maximize some desired performance.The quality of the resulting policies are compared with a simple baseline to evaluate the system and derive guidelines to adopt this technique in different use cases. The main contribution of this paper is a flexible and extensible OpenAI Gym environment, which allows to generate, evaluate, and compare policies for autonomous multi-drone systems in multi-service applications. This environment allows for comparative evaluation and benchmarking of different approaches in a variety of application contexts.