# Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.04317 · HTML: https://mlsanity.com/paper/2505.04317/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 7 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

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

- [AgilePE: Autonomous UAV Pursuit-Evasion via Self-Play Reinforcement Learning](https://mlsanity.com/paper/2608.14135/) (2026)
- [Game-Guided Skill Discovery through Self-Play for Playable Agent Control](https://mlsanity.com/paper/2609.40137/) (2026)

## Abstract (arXiv)

In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control. The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to its long-horizon dependencies, tight inter-agent coupling, and the underactuated dynamics of quadrotors. To address this, we propose Hierarchical Co-Self-Play (HCSP), a hierarchical reinforcement learning framework that separates centralized high-level strategic decision-making from decentralized low-level motion control. We design a three-stage population-based training pipeline to enable both strategy and skill to emerge from scratch without expert demonstrations: (I) training diverse low-level skills, (II) learning high-level strategy via self-play with fixed low-level skills, and (III) joint fine-tuning through co-self-play. Experiments show that HCSP achieves superior performance, outperforming non-hierarchical self-play and rule-based hierarchical baselines with an average 82.9% win rate and a 71.5% win rate against the two-stage variant. Moreover, co-self-play leads to emergent team behaviors such as role switching and coordinated formations, demonstrating the effectiveness of our hierarchical design and training scheme. The project page is at https://hi-co-self-play.github.io.