Compared with IP multicast, Overlay Multicast (OM) offers better compatibility and flexible deployment in heterogeneous, cross-domain networks. However, traditional OM struggles to adapt to dynamic traffic due to unawareness of physical resource states, and existing reinforcement learning methods fail to decouple OM's tightly coupled multi-objective nature, leading to high complexity, slow convergence, and instability. To address this, we propose MA-DHRL-OM, a multi-agent deep hierarchical reinforcement learning approach. Using SDN's global view, it builds a traffic-aware model for OM path planning. The method decomposes OM tree construction into two stages via hierarchical agents, reducing action space and improving convergence stability. Multi-agent collaboration balances multi-objective optimization while enhancing scalability and adaptability. Experiments show MA-DHRL-OM outperforms existing methods in delay, bandwidth utilization, and packet loss, with more stable convergence and flexible routing.