用注意力机制解决无人机群异构协作中的依赖不对称问题。
AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination
- 引入角色感知的注意力机制建模异构智能体间不对称依赖。
- 通过分阶段课程学习提升成功率，降低遗忘风险。
- 适合研究多智能体强化学习与无人机协同控制的读者。
异构无人机群的协同路径规划对多智能体强化学习（MARL）提出巨大挑战，尤其在处理智能体间非对称依赖关系，以及稀疏奖励和灾难性遗忘等问题时。本文提出一种有注意力建构的课程学习框架（AC-MASAC）。该框架引入角色感知的异构注意力机制，显式建模非对称依赖关系；并设计结构化课程策略，融合分层知识迁移与阶段比例经验回放，以缓解稀疏奖励与灾难性遗忘问题。在自研多智能体仿真平台上验证表明，本方法在成功率、编队保持率及加权任务完成时间上显著优于其他先进方法。代码已公开于：https://github.com/Wanhao-Liu/AC-MASAC。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。