Light Aircraft Game : Basic Implementation and training results analysis
This work addresses algorithm selection for cooperative-competitive multi-agent systems, but it is incremental as it evaluates existing methods on a new environment.
The paper tackles multi-agent reinforcement learning in a partially observable combat environment called LAG, finding that HASAC performs well in simpler coordination tasks without weapons, while HAPPO shows stronger adaptability in dynamic missile combat scenarios.
This paper investigates multi-agent reinforcement learning (MARL) in a partially observable, cooperative-competitive combat environment known as LAG. We describe the environment's setup, including agent actions, hierarchical controls, and reward design across different combat modes such as No Weapon and ShootMissile. Two representative algorithms are evaluated: HAPPO, an on-policy hierarchical variant of PPO, and HASAC, an off-policy method based on soft actor-critic. We analyze their training stability, reward progression, and inter-agent coordination capabilities. Experimental results show that HASAC performs well in simpler coordination tasks without weapons, while HAPPO demonstrates stronger adaptability in more dynamic and expressive scenarios involving missile combat. These findings provide insights into the trade-offs between on-policy and off-policy methods in multi-agent settings.