This codebase is a pre-released implementation of MaskDP.
TODO: clean up codebase, upload models and datasets.
Install MuJoCo if it is not already the case:
- Download MuJoCo binaries here.
- Unzip the downloaded archive into
~/.mujoco/
. - Append the MuJoCo subdirectory bin path into the env variable
LD_LIBRARY_PATH
.
Install the following libraries:
sudo apt update
sudo apt install libosmesa6-dev libgl1-mesa-glx libglfw3 unzip
Install dependencies:
conda env create -f conda_env.yml
conda activate maskdp
In this paper, we use unsupervised/semi/supervised data collected based on ExoRL. You can follow the repo and collect offline data as described in our appendix. You can also collect your own offline data.
We provide example in example_scripts
to train or evaluate the model. Please modify the path to your local dataset.