Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Wanhao, Dai, Junhong, Zhang, Yixuan, Yin, Shengyun, Li, Panshuo
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.11735
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917270307995648
author Liu, Wanhao
Dai, Junhong
Zhang, Yixuan
Yin, Shengyun
Li, Panshuo
author_facet Liu, Wanhao
Dai, Junhong
Zhang, Yixuan
Yin, Shengyun
Li, Panshuo
contents Cooperative path planning for heterogeneous UAV swarms poses significant challenges for Multi-Agent Reinforcement Learning (MARL), particularly in handling asymmetric inter-agent dependencies and addressing the risks of sparse rewards and catastrophic forgetting during training. To address these issues, this paper proposes an attentive curriculum learning framework (AC-MASAC). The framework introduces a role-aware heterogeneous attention mechanism to explicitly model asymmetric dependencies. Moreover, a structured curriculum strategy is designed, integrating hierarchical knowledge transfer and stage-proportional experience replay to address the issues of sparse rewards and catastrophic forgetting. The proposed framework is validated on a custom multi-agent simulation platform, and the results show that our method has significant advantages over other advanced methods in terms of Success Rate, Formation Keeping Rate, and Success-weighted Mission Time. The code is available at \textcolor{red}{https://github.com/Wanhao-Liu/AC-MASAC}.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11735
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination
Liu, Wanhao
Dai, Junhong
Zhang, Yixuan
Yin, Shengyun
Li, Panshuo
Robotics
Cooperative path planning for heterogeneous UAV swarms poses significant challenges for Multi-Agent Reinforcement Learning (MARL), particularly in handling asymmetric inter-agent dependencies and addressing the risks of sparse rewards and catastrophic forgetting during training. To address these issues, this paper proposes an attentive curriculum learning framework (AC-MASAC). The framework introduces a role-aware heterogeneous attention mechanism to explicitly model asymmetric dependencies. Moreover, a structured curriculum strategy is designed, integrating hierarchical knowledge transfer and stage-proportional experience replay to address the issues of sparse rewards and catastrophic forgetting. The proposed framework is validated on a custom multi-agent simulation platform, and the results show that our method has significant advantages over other advanced methods in terms of Success Rate, Formation Keeping Rate, and Success-weighted Mission Time. The code is available at \textcolor{red}{https://github.com/Wanhao-Liu/AC-MASAC}.
title AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination
topic Robotics
url https://arxiv.org/abs/2602.11735