This is the implementation of RLAD, which is described in:

RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environments

Daniel Coelho, Miguel Oliveira, Vítor Santos.

IEEE Transactions on Automation Science and Engineering

If you find our work useful, please consider citing:

@ARTICLE{10364974,
  author={Coelho, Daniel and Oliveira, Miguel and Santos, Vítor},
  journal={IEEE Transactions on Automation Science and Engineering}, 
  title={RLAD: Reinforcement Learning From Pixels for Autonomous Driving in Urban Environments}, 
  year={2023},
  volume={},
  number={},
  pages={1-9},
  keywords={Training;Task analysis;Reinforcement learning;Autonomous vehicles;Visualization;Convolution;Urban areas;Autonomous driving;reinforcement learning;deep learning;feature representation;deep neural networks},
  doi={10.1109/TASE.2023.3342419}}

• Clone the repository with git clone [email protected]:DanielCoelho112/rlad.git
• Download CARLA 0.9.10.1.
• Run the docker container with docker run -it --gpus all --network=host -v results_path:/root/results/rlad -v rlad_path:/root/rlad danielc11/rlad:0.0 bash where results_path is the path where the results will be written, and rlad_path is the path of the rlad repository.

• Start the CARLA server
• Run: python3 rlad/run/python3 main.py -en rlad_original

Thanks to the authors of End-to-End Urban Driving by Imitating a Reinforcement Learning Coach for providing a framework to train RL agent in CARLA.