# Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Coordination by Multi-Critic Policy Gradient Optimization

arXiv: https://arxiv.org/abs/2012.15472 · HTML: https://mlsanity.com/paper/2012.15472/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2209.10113/) (2022)
- [Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective](https://mlsanity.com/paper/2106.05402/) (2021)
- [Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning](https://mlsanity.com/paper/2306.17052/) (2023)
- [Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2110.08642/) (2021)
- [Current applications and potential future directions of reinforcement learning-based Digital Twins in agriculture](https://mlsanity.com/paper/2406.08854/) (2024)

## Abstract (arXiv)

Recent technological progress in the development of Unmanned Aerial Vehicles (UAVs) together with decreasing acquisition costs make the application of drone fleets attractive for a wide variety of tasks. In agriculture, disaster management, search and rescue operations, commercial and military applications, the advantage of applying a fleet of drones originates from their ability to cooperate autonomously. Multi-Agent Reinforcement Learning approaches that aim to optimize a neural network based control policy, such as the best performing actor-critic policy gradient algorithms, struggle to effectively back-propagate errors of distinct rewards signal sources and tend to favor lucrative signals while neglecting coordination and exploitation of previously learned similarities. We propose a Multi-Critic Policy Optimization architecture with multiple value estimating networks and a novel advantage function that optimizes a stochastic actor policy network to achieve optimal coordination of agents. Consequently, we apply the algorithm to several tasks that require the collaboration of multiple drones in a physics-based reinforcement learning environment. Our approach achieves a stable policy network update and similarity in reward signal development for an increasing number of agents. The resulting policy achieves optimal coordination and compliance with constraints such as collision avoidance.