# A Differential Game Approach for Beyond Visual Range Tactics

arXiv: https://arxiv.org/abs/2009.10640 · HTML: https://mlsanity.com/paper/2009.10640/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 2 of 2)

- [Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions](https://mlsanity.com/paper/2307.06152/) (2023)
- [Maneuver Decision-Making Through Proximal Policy Optimization And Monte Carlo Tree Search](https://mlsanity.com/paper/2309.08611/) (2023)

## Abstract (arXiv)

An operational relevant conflict between teams of autonomous vehicles in the Beyond Visual Range domain is addressed in this paper. Optimal strategies are designed in order for a team of air interceptors to protect a high value asset and block the attacking team at a safe distance from such asset. The attacking agents take specific roles of leader and wingman and also devise their own optimal strategies in order to launch an attack as close as possible from the asset. The problem is formulated as a zero-sum differential game between players with different speed over two stages: the attack and the retreat stages. For each stage the state-feedback optimal strategies of each player are derived in analytical form.