Pope, Adrian, P (Primordial Labs), Ide, Jaime, S. (Yale University & Lockheed Martin), Micovic, Daria (Lockheed Martin), Diaz, Henry (Lockheed Martin), Rosenbluth, David (Lockheed Martin), Ritholtz, Lee (Lockheed Martin), Twedt, Jason (Lockheed Martin), Walker, Thayne (University of Denver & Lockheed Martin), Alcedo, Kevin (Lockheed Martin), Javorsek, Daniel (US Airforce)

Hierarchical Reinforcement Learning for Air-To-Air Combat

Scheduled for presentation during the Regular Session "Learning Methods II" (WeB2), Wednesday, June 16, 2021, 15:00−15:20, Kozani

2021 International Conference on Unmanned Aircraft Systems (ICUAS), June 15-18, 2021, Athens, Greece

This information is tentative and subject to change. Compiled on April 26, 2024

Abstract

Artificial Intelligence (AI) is becoming a critical component in the defense industry, as recently demonstrated by DARPA‘s AlphaDogfight Trials (ADT). ADT sought to vet the feasibility of AI algorithms capable of piloting an F-16 in simulated air-to-air combat. As a participant in ADT, Lockheed Martin‘s (LM) approach combines a hierarchical architecture with maximum-entropy reinforcement learning (RL), integrates expert knowledge through reward shaping, and supports modularity of policies. This approach achieved a 2nd place finish in the final ADT event (among eight total competitors) and defeated a graduate of the US Air Force’s (USAF) F-16 Weapons Instructor Course in match play.