NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation (Supplementary Material)

We make use of four internal 12 GB NVIDIA TITAN Xp GPUs to perform our experiments. At initialization of each environment, four UEs are randomly stationed 1.5 meters above the The LTE base station lies at (x, z) = (40m, 3m). The only change in the configuration file between episodes is the random_seed parameter. We use random seed values from 0 to 63, inclusive, for this parameter. We store the resulting three offline datasets in the NetworkAgent/buffers directory.