This repository contains code associated with A Benchmark Comparison of Imitation Learning-based Control Policies for Autonomous Racing
Clone this repository
git clone https://github.com/mlab-upenn/f1tenth_il.gitNavigate to the root directory of this project
cd f1tenth_ilCreate a new conda environment with Python 3.8
conda create -n f110_il python=3.8Activate the environment
conda activate f110_ilInstall pip
conda install pip Install the dependencies for F1TENTH gym.
pip install -e .Install other dependencies
pip install -r requirements.txtNavigate to the imitation learning folder
cd imitation_learningExecute the training script
python train.py --algorithm=<algorithm name> --training_config=<yaml file location>Example:
python train.py --algorithm=hg-dagger --training_config=il_config.yamlNavigate to the imitation learning folder
cd imitation_learningExecute the inference script
python inference.py --training_config=<yaml file location> --model_path=<model path>Example:
python inference.py --training_config=il_config.yaml --model_path=logs/HGDAgger_model.pkl