# Light Aircraft Game : Basic Implementation and training results analysis

arXiv: https://arxiv.org/abs/2506.14164 · HTML: https://mlsanity.com/paper/2506.14164/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multi-agent reinforcement learning, one of 15 directions in Deep reinforcement learning methods.
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [Multi-agent reinforcement learning](https://mlsanity.com/deeprl/multi-agent-reinforcement-learning/)

## Builds on (most cited first, 6 of 6)

- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [FACMAC: Factored Multi-Agent Centralised Policy Gradients](https://mlsanity.com/paper/2003.06709/) (2020)
- [A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https://mlsanity.com/paper/1706.10059/) (2017)
- [Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2206.08686/) (2022)

## Built on by (most cited first, 1 of 1)

- [BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learning](https://mlsanity.com/paper/2608.25419/) (2026)

## Abstract (arXiv)

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.