• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Service-Oriented System Engineering >Learning to Communicate Efficiently with Group Division in Decentralized Multi-agent Cooperation
【24h】

Learning to Communicate Efficiently with Group Division in Decentralized Multi-agent Cooperation

机译：在分散的多主体合作中学习与团队部门进行有效沟通

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recent advances in multi-agent reinforcement learning show that agents can spontaneously learn when and what to communicate with each other to support effective cooperation. However, the existing approaches assume a fully-connected network with unlimited bandwidth, which is impractical in many real-world scenarios. For instance, in many multi-robot applications, robots are connected only through an unstable wireless network with limited bandwidth. Therefore, we must enable the agents to learn communication strategy that takes the consumption of network resources into account. This paper proposes a group division-based attentional communication model (GDAC), which can divide agents into groups according to their 'attention' in the learned communication strategy. According to the novel 'attention' mechanism, agents can be dynamically grouped according to their task relevance, and the communication only takes places inside the same group. As a result, it avoids a fully-connected communication architecture and can significantly reduce the bandwidth consumption at runtime. This model has been successfully applied to the environmental exploration task with a group of agents. The results show that GDAC could effectively reduce the total amount of communication message and yield improved performance over the existing fully-connected communication architecture.
机译：多主体强化学习的最新进展表明，主体可以自发地学习何时以及如何相互交流以支持有效的合作。但是，现有方法假定具有无限带宽的完全连接的网络，这在许多实际场景中是不切实际的。例如，在许多多机器人应用中，仅通过带宽有限的不稳定无线网络连接机器人。因此，我们必须使代理能够学习考虑网络资源消耗的通信策略。本文提出了一种基于分组划分的注意交流模型（GDAC），该模型可以根据学习者在交流策略中的“注意力”将其分为几类。根据新颖的“注意力”机制，可以根据代理的任务相关性对代理进行动态分组，并且通信仅在同一组内部进行。结果，它避免了完全连接的通信体系结构，并可以显着减少运行时的带宽消耗。该模型已与一组代理一起成功地应用于环境勘探任务。结果表明，与现有的全连接通信体系结构相比，GDAC可以有效地减少通信消息的总量并提高性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号