GROVE, a generalized reward framework that enables open-vocabulary pkysical skill leaning without manual engineering or task-specific demonstrations.

• Release training and inference code of Pose2CLIP.
• Release well-trained model of Pose2CLIP.
• Release the training data of low-level controller.
• Release training code of basic RL agents.

Download Isaac Gym from the website, then follow the installation instructions.

Once Isaac Gym is installed, install the external dependencies for this repo:

pip install -r requirements.txt

We release all our training motions for low-level controller, which are located in calm/data/motions/.Individual motion clips are stored as .npy files. Motion datasets are specified by .yaml files, which contains a list of motion clips to be included in the dataset. Motion clips can be visualized with the following command:

python calm/run.py
--test
--task HumanoidViewMotion
--num_envs 1
--cfg_env calm/data/cfg/humanoid.yaml
--cfg_train calm/data/cfg/train/rlg/amp_humanoid.yaml
--motion_file [Your file path].npy

--motion_file can be used to visualize a single motion clip .npy or a motion dataset .yaml. If you want to retarget new motion clips to the character, you can take a look at an example retargeting script in calm/poselib/retarget_motion.py.

Our code is based on CALM and CLIP and AnySkill. Thanks for these great projects.

@inproceedings{cui2025grove,
  title={GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill},
  author={Cui, Jieming and Liu, Tengyu and Ziyu, Meng and Jiale, Yu and Ran Song and Wei Zhang and Zhu, Yixin and Huang, Siyuan},
  booktitle={Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2025}
}