多智能体无人机群中三层次学习动态可被严格约束，确保系统稳定运行。
Bounded Coupled AI Learning Dynamics in Tri-Hierarchical Drone Swarms
- 构建三层次学习架构：局部突触学习、群体强化学习、战略元学习协同运行
- 证明误差随时间不发散，且各层状态漂移有界，系统整体性能可控
- 适用于高可靠性无人机集群、自动驾驶等需长期稳定协同的场景
现代自主多智能体系统融合异构学习机制，运行于不同时间尺度。本文研究三层次无人机集群学习系统：（1）个体层面的局部赫布在线学习（快时标，10-100毫秒）；（2）多智能体强化学习（MARL）实现战术群体协作（中时标，1-10秒）；（3）元学习（MAML）支持战略适应（慢时标，10-100秒）。建立四项理论结果：有界总误差定理表明，在学习率约束、映射利普希茨连续性及权重稳定条件下，总次优性在时间上具分量级统一上界；有界表征漂移定理给出赫布更新对协调层嵌入的影响最坏估计；元层相容性定理提供战略适应保持底层不变量的充分条件；非累积定理证明误差不会随时间无界增长。
原文摘要 · Abstract (English)
Modern autonomous multi-agent systems combine heterogeneous learning mechanisms operating at different timescales. An open question remains: can one formally guarantee that coupled dynamics of such mechanisms stay within the admissible operational regime? This paper studies a tri-hierarchical swarm learning system where three mechanisms act simultaneously: (1) local Hebbian online learning at individual agent level (fast timescale, 10-100 ms); (2) multi-agent reinforcement learning (MARL) for tactical group coordination (medium timescale, 1-10 s); (3) meta-learning (MAML) for strategic adaptation (slow timescale, 10-100 s). Four results are established. The Bounded Total Error Theorem shows that under contractual constraints on learning rates, Lipschitz continuity of inter-level mappings, and weight stabilization, total suboptimality admits a component-wise upper bound uniform in time. The Bounded Representation Drift Theorem gives a worst-case estimate of how Hebbian updates affect coordination-level embeddings during one MARL cycle. The Meta-Level Compatibility Theorem provides sufficient conditions under which strategic adaptation preserves lower-level invariants. The Non-Accumulation Theorem proves that error does not grow unboundedly over time.
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。