# A Deep Ensemble Multi-Agent Reinforcement Learning Approach for Air Traffic Control

arXiv: https://arxiv.org/abs/2004.01387 · HTML: https://mlsanity.com/paper/2004.01387/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 4 of 4)

- [Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance](https://mlsanity.com/paper/2105.02331/) (2021)
- [Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers](https://mlsanity.com/paper/2206.07403/) (2022)
- [Data-driven prediction of Air Traffic Controllers reactions to resolving conflicts](https://mlsanity.com/paper/2205.09539/) (2022)
- [A Future Capabilities Agent for Tactical Air Traffic Control](https://mlsanity.com/paper/2601.04285/) (2026)

## Abstract (arXiv)

Air traffic control is an example of a highly challenging operational problem that is readily amenable to human expertise augmentation via decision support technologies. In this paper, we propose a new intelligent decision making framework that leverages multi-agent reinforcement learning (MARL) to dynamically suggest adjustments of aircraft speeds in real-time. The goal of the system is to enhance the ability of an air traffic controller to provide effective guidance to aircraft to avoid air traffic congestion, near-miss situations, and to improve arrival timeliness. We develop a novel deep ensemble MARL method that can concisely capture the complexity of the air traffic control problem by learning to efficiently arbitrate between the decisions of a local kernel-based RL model and a wider-reaching deep MARL model. The proposed method is trained and evaluated on an open-source air traffic management simulator developed by Eurocontrol. Extensive empirical results on a real-world dataset including thousands of aircraft demonstrate the feasibility of using multi-agent RL for the problem of en-route air traffic control and show that our proposed deep ensemble MARL method significantly outperforms three state-of-the-art benchmark approaches.