The simulation code for the paper:
"AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning"
The overall architecture of the proposed MARL framework is shown in the figure.
Modified MADDPG: This algorithm trains two critics (different from legacy MADDPG) with the following functionalities:
The trace location in Seoul, South Korea has an area spanning over 2.5 × 1.5 km where there are are more than 30 intersections. A number of simulated vehicles are moving in the road topology. Each vehicle shows following properties for every second:
timestep(simulation) secondsThe time step described by the values within this timestep-element
ididThe id of the vehicle
typeidThe name of the vehicle type
speedm/sThe speed of the vehicle