A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.
First, thank you for your code.
But I run so slow both on sumo and sumo-gui, when I change the network from full-connected to CNN. Can you tell me why the simulation run so slow, ten minute gone, I still can't see one episode result.
I am sorry but your problem seems not related to an issue on the repo code. My advice is to profile your code to check where the algorithm is taking so much time.
First, thank you for your code. But I run so slow both on sumo and sumo-gui, when I change the network from full-connected to CNN. Can you tell me why the simulation run so slow, ten minute gone, I still can't see one episode result.