drone
is a reinforcement learning based drone controller and simulator tool for the Warwick AI drone project.
Install the required packages - which are outlined in pyproject.toml
.
They can be installed with pip
or a Python package management tool such as uv
.
git clone https://github.com/stmio/drone.git
uv sync
To open the matplotlib visualisation tool, run the following command:
# If installed with pip
python drone.py
# If installed with uv
uv run drone.py
To train the model, run the following command:
python simulator/ppo.py --env_id DroneEnv-v0
# If installed with uv
uv run simulator/ppo.py --env_id DroneEnv-v0
You can also use wandb to visualise the training process (requires an account):
python simulator/ppo.py --track --wandb-project-name drone --env_id DroneEnv-v0
# If installed with uv
uv run simulator/ppo.py --track --wandb-project-name drone --env_id DroneEnv-v0
Screen.Recording.2024-11-10.at.11.49.31.mov
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, shall be licensed as above, without any additional terms or conditions.