GitHub - jiemingcui/GROVE-pytorch: [CVPR'25 Oral] "GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill" (original) (raw)

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

TODOs

• 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.

Installation

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

Training Data

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.

Acknowledgments

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

Citation

@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}
}