Fighter Jet Navigation and Combat using Deep Reinforcement Learning with Explainable AI
Swati Kar, Soumyabrata Dey, Mahesh K Banavar, Shahnewaz Karim Sakib
TL;DR
The paper addresses autonomous fighter-jet navigation and combat as a multi-objective DRL problem within a custom Pygame simulator. It deploys a Double Deep Q-Network (DDQN) with a carefully designed reward function that balances navigation efficiency, resource management, and engagement outcomes, accompanied by an $\epsilon$-greedy strategy decaying from $\epsilon_0=1.0$ to $\epsilon_f=0.1$. Explainability is achieved through factual and counterfactual reward analyses and action-distribution insights, providing transparency into the learned policy. Results show an 82.5% success rate over 1000 evaluation episodes and demonstrate stable learning with coherent policy behavior across navigation and engagement tasks.
Abstract
This paper presents the development of an Artificial Intelligence (AI) based fighter jet agent within a customized Pygame simulation environment, designed to solve multi-objective tasks via deep reinforcement learning (DRL). The jet's primary objectives include efficiently navigating the environment, reaching a target, and selectively engaging or evading an enemy. A reward function balances these goals while optimized hyperparameters enhance learning efficiency. Results show more than 80\% task completion rate, demonstrating effective decision-making. To enhance transparency, the jet's action choices are analyzed by comparing the rewards of the actual chosen action (factual action) with those of alternate actions (counterfactual actions), providing insights into the decision-making rationale. This study illustrates DRL's potential for multi-objective problem-solving with explainable AI. Project page is available at: \href{https://github.com/swatikar95/Autonomous-Fighter-Jet-Navigation-and-Combat}{Project GitHub Link}.