Coordinated Strategies in Realistic Air Combat by Hierarchical Multi-Agent Reinforcement Learning
This work addresses the problem of coordinated strategies in realistic air combat for military or simulation applications, but it appears incremental as it builds on existing hierarchical and multi-agent reinforcement learning techniques.
The paper tackled the challenge of achieving mission objectives in realistic aerial combat simulations with imperfect situational awareness and nonlinear flight dynamics by introducing a novel 3D multi-agent air combat environment and a Hierarchical Multi-Agent Reinforcement Learning framework. The result showed improved learning efficiency and combat performance in complex dogfight scenarios, though no concrete numbers were provided.
Achieving mission objectives in a realistic simulation of aerial combat is highly challenging due to imperfect situational awareness and nonlinear flight dynamics. In this work, we introduce a novel 3D multi-agent air combat environment and a Hierarchical Multi-Agent Reinforcement Learning framework to tackle these challenges. Our approach combines heterogeneous agent dynamics, curriculum learning, league-play, and a newly adapted training algorithm. To this end, the decision-making process is organized into two abstraction levels: low-level policies learn precise control maneuvers, while high-level policies issue tactical commands based on mission objectives. Empirical results show that our hierarchical approach improves both learning efficiency and combat performance in complex dogfight scenarios.