Autonomous Agent for Beyond Visual Range Air Combat: A Deep Reinforcement Learning Approach

TL;DR

This paper develops a deep reinforcement learning-based autonomous agent for beyond visual range air combat, aiming to improve tactics and pilot training through simulation and self-play experiments.

Contribution

It introduces a deep reinforcement learning agent for BVR air combat that learns and adapts tactics, and explores interactions with real pilots in virtual environments.

Findings

Agent demonstrates high-performance combat behavior

Self-play generates novel air combat tactics

Potential to enhance pilot training and air defense strategies

Abstract

This work contributes to developing an agent based on deep reinforcement learning capable of acting in a beyond visual range (BVR) air combat simulation environment. The paper presents an overview of building an agent representing a high-performance fighter aircraft that can learn and improve its role in BVR combat over time based on rewards calculated using operational metrics. Also, through self-play experiments, it expects to generate new air combat tactics never seen before. Finally, we hope to examine a real pilot's ability, using virtual simulation, to interact in the same environment with the trained agent and compare their performances. This research will contribute to the air combat training context by developing agents that can interact with real pilots to improve their performances in air defense missions.