基于注意力的分层变分信息瓶颈用于可变带宽下鲁棒的多智能体通信
Attention-based Hierarchical Variational Information Bottleneck for Robust Multi-Agent Communication under Variable Bandwidth
浏览论文内容
中文总结 AI 辅助
提出AH-VIB模型，结合变分信息瓶颈与自回归生成，在可变带宽下实现鲁棒的多智能体通信，提升受限带宽下的性能可靠性。
中文摘要 AI 辅助
在有限带宽下基于学习的多智能体通信不仅需要决定通信内容，还需要构建消息结构，使得部分传输仍然有用。我们在前缀截断条件下研究此问题，其中每条消息仅接收第一部分。为解决此问题，我们提出AH-VIB，一种基于注意力的自回归变分通信模型，该模型结合了变分信息瓶颈（VIB）与顺序消息生成以及分层鲁棒性损失。我们在自定义的协作式物体检查和占用映射任务上评估AH-VIB，其中配备有限视场传感器的智能体在占用网格世界中协调扫描检查物体，在可变和固定带宽条件下，并将其与MADDPG、CommNet、扁平VIB基线和自回归MLP消融进行比较。AH-VIB在最具限制性的带宽条件下实现了有竞争力的平均回报，同时提高了性能可靠性。这些结果表明，AH-VIB在带宽约束下提高了学习通信的可靠性和优雅降级能力。
英文摘要
Learning-based multi-agent communication under limited bandwidth does not only require deciding what to communicate, but also structuring messages so that partial transmissions remain useful. We study this problem under prefix truncation, where only the first part of each message is received. To address it, we propose \textbf{AH-VIB}, an attention-based autoregressive variational communication model that combines a variational information bottleneck (VIB) with sequential message generation and a hierarchical robustness loss. We evaluate AH-VIB on a custom cooperative object-inspection and occupancy-mapping task, where agents equipped with a limited field-of-view sensor coordinate to scan inspection objects in an occupancy-grid world, under variable and fixed bandwidth conditions, and compare it against MADDPG, CommNet, a flat VIB baseline, and an autoregressive MLP ablation. AH-VIB achieves competitive mean return while improving performance reliability under the most constrained bandwidth conditions. These results indicate that AH-VIB improves the reliability and graceful degradation of learned communication under bandwidth constraints.
发表机构
- Aarhus University（奥胡斯大学）
- EIVA a/s（EIVA公司）
- DIGIT, Aarhus University（奥胡斯大学DIGIT）
机构由 AI 辅助整理，请以论文原文为准。
