Search papers, labs, and topics across Lattice.
This paper introduces BVR Sim, an open-source environment tailored for heterogeneous air-combat reinforcement learning, addressing challenges such as partial observability and energy management. The platform supports various aircraft models and features a unified tactical action interface, allowing for seamless policy application across different platforms. Key results show that a policy trained on the F-16 can effectively transfer to other aircraft, achieving a 45.5% mean win rate without retraining, demonstrating the environment's versatility and practical applicability in multi-agent scenarios.
A policy trained on one aircraft can successfully adapt to multiple others, achieving impressive performance without any retraining.
Beyond-visual-range (BVR) air combat is a challenging reinforcement-learning domain characterized by partial observability, long-horizon decision making, energy management, and limited weapons. We present BVR Sim, an open-source Gymnasium-style environment designed for heterogeneous air-combat reinforcement learning. BVR Sim supports multiple JSBSim aircraft models, including the F-15, F-16, F/A-18, and F-22, with configurable weapons, sensors, controllers, and opponents. A unified tactical action interface specifies desired heading, altitude, speed, and weapon release above aircraft-specific inner-loop controllers, enabling policies to operate across heterogeneous platforms. The environment provides interchangeable Python and accelerated C++ backends, entity-oriented observations, compositional rewards, scripted opponents, replay and visualization, and adapters for multi-agent learning frameworks. At a 0.4-s decision interval, the C++ backend achieves 104 simulated seconds per wall-clock second in 1-vs-1 and remains practical through 10-vs-10 scenarios. A policy trained only on the F-16 transfers without retraining to four unseen aircraft, reaching a 45.5% mean win rate with aircraft-specific controller adaptation. MAPPO and HAPPO experiments further verify end-to-end compatibility with standard multi-agent reinforcement-learning pipelines.
