- Clone the repo
git clone [email protected]:bennevans/iida.git
cd iida/
-
Install MuJoCo here.
-
Install the required python packages:
conda env create -f setup/environment.yaml
OR
cd setup/
pip install -r requirements.txt
- Install the
varyingsim
library
pip install -e .
- Generate the simulated dataset or download it here.
cd scripts/dataset/
python create_da_dataset_push_box.py
python create_da_dataset_slide_puck.py
To train a policy to generate rollouts, I use mjrl.
cd scripts/policy/
python train_policy.py
python relabel_paths.py --env <env>
To run with the current experiment and algorithm parameters:
cd scripts/
And run:
python run_exp.py -c <config file>.yaml