Experiments require MuJoCo. Follow the instructions in the mujoco-py repo to install. Then, dependencies can be installed with the following command:
conda env create -f conda_env.yml
Datasets are stored in the data
directory.
Install the D4RL repo, following the instructions there.
Then, run the following script in order to download the datasets and save them in our format:
python download_d4rl_datasets.py
Experiments can be reproduced with the following:
python experiment.py --env hopper --dataset medium --model_type dt
Adding -w True
will log results to Weights and Biases.