Project developed for Sapienza Honor's Programme. The project aims at developing a reinforcement learning application to make an agent drive safely in acondition of dense traffic. For doing so, SUMO was used to simulate the behaviour of the ego vehicletogether with a fleet of autonomous vehicles and to train two model of RL algorithms, namely DQNand A2C.The development flow was the following: creating the highway with NetEdit, get the parameters of thesimulation, create a custom Gym environment and train the networks
First install SUMO and then the required packages from requirements.txt
I wrote a report about this. You can find it inside report folder