We consider a dynamic millimeter-wave network with integrated access and backhaul, where mobile relay nodes move to auto-reconfigure the wireless backhaul. Specifically, we focus on in-band relaying networks, which conduct access and backhaul links on the same frequency band with severe constraints on co-channel interference. In this context, we jointly study the complex problem of dynamic relay node positioning, user association, and backhaul capacity allocation. To address this problem, with limited complexity, we adopt a hierarchical multi-agent reinforcement with a two-level structure. A high-level policy dynamically coordinates mobile relay nodes, defining the backhaul configuration for a low-level policy, which jointly assigns user equipment to each relay and allocates the backhaul capacity accordingly. The resulting solution automatically adapts the access and backhaul network to changes in the number of users, the traffic distribution, and the variations of the channels. Numerical results show the effectiveness of our proposed solution in terms of convergence of the hierarchical learning procedure. It also provides a significant backhaul capacity and network sum-rate increase (up to 3.5x) compared to baseline approaches.

翻译：我们考虑一个具有集成接入与回传的动态毫米波网络，其中移动中继节点通过移动以自动重构无线回传链路。具体而言，我们聚焦于带内中继网络，该网络在相同频段上同时进行接入与回传链路，并受到同信道干扰的严格约束。在此背景下，我们联合研究动态中继节点定位、用户关联及回传容量分配这一复杂问题。为在有限复杂度下解决该问题，我们采用一种具有双层结构的分层多智能体强化学习方法。高层策略动态协调移动中继节点，为低层策略定义回传配置；低层策略则联合为每个中继分配用户设备并据此分配回传容量。所提方案能自动调整接入与回传网络以适应用户数量、流量分布及信道变化。数值结果验证了该方案在分层学习收敛性方面的有效性，同时与基线方法相比，其显著提升了回传容量与网络总速率（最高达3.5倍）。