Proximity-Based Reward Systems for Multi-Agent Reinforcement Learning

Unmanned vehicles, such as drones, have surged in popularity in recent years. Swarms of these vehicles offer new opportunities in applications such as agriculture, weather monitoring and natural events management. However, efficiently controlling a large swarm of unmanned vehicles poses a significant challenge. Intelligent solutions, particularly reinforcement learning, have been proposed to address this challenge. We introduce a proximity-based reward system for multi-agent reinforcement learning to handle the issue of reward sparsity. Our goal is to develop an approach for controlling a swarm towards a common objective while maintaining robust swarm cohesion. In this paper, we compare various distance-based functions to build a comprehensive reward system. Specifically, we explore the Euclidean, Manhattan, Chebyshev and Minkowski distances in our experiments. We evaluate the impact of these proximity-based reward systems on four reinforcement learning algorithms. We conduct a comparison of our reward systems using various metrics during validation and test episodes. Our goal is to highlight the importance of comparing different algorithms and distance functions in the development of multiagent reinforcement learning systems.