I've been trying to produce result for the paper of Deep Reinforcement Learning-Based Resource Allocation in Cooperative UAV-Assisted Wireless Networks. I am having difficulties in understanding logic of Phase2: Transmission from UAVs to UE which I only implemented set of UE group associated to UAV, not randomly distributed as in the paper. I'm wondering if someone can help me. I'd appreciate if I can get source code as a reference. Thank you.