Explainable Reinforcement Learning for assisting Air Traffic Controllers

As AI moves into safety-critical domains like aviation, healthcare, and autonomous driving, trust hinges on explainability. This work applies explainability techniques to a reinforcement learning agent trained in a simplified air traffic control environment, where the agent chooses alternative flight routes to avoid no-fly zones. Using saliency maps, the authors expose which input features most influence the agent's routing decisions. The approach offers a preliminary but concrete path toward human-interpretable AI decision support for controllers, with potential application in building operator trust, certifying AI-assisted aviation tools, and extending explainability methods to other high-stakes automated decision systems. Authors: Anduel Mehmeti, Gabriella Gigante, Salvatore Venticinque Paper: https://arxiv.org/abs/2607.22525v1