ManiSkill-Learn
ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a physics-rich manipulation skill benchmark with large-scale demonstrations.
File Explorer
Download Latest Version (.zip)- bc.py
- bc_mani_skill.py
- bc_mani_skill_pointnet.py
- bc_mani_skill_pointnet_seg.py
- bc_mani_skill_pointnet_transformer.py
- bcq.py
- bcq_mani_skill.py
- bcq_mani_skill_pointnet.py
- bcq_mani_skill_pointnet_transformer.py
- cql.py
- cql_mani_skill.py
- cql_mani_skill_pointnet.py
- cql_mani_skill_pointnet_transformer.py
- sac.py
- sac_mani_skill_mlp.py
- td3_bc.py
- td3_bc_mani_skill.py
- td3_bc_mani_skill_pointnet.py
- td3_bc_mani_skill_pointnet_transformer.py
- mani_skill_point_cloud.py
- mani_skill_point_cloud_seg.py
- mani_skill_point_cloud_transformer.py
- mani_skill_point_cloud_transformer_disk.py
- mani_skill_state.py
- mani_skill_state_multiple_datasets.py
- mani_skill_point_cloud.py
- mani_skill_point_cloud_transformer.py
- mani_skill_state.py
- mani_skill_point_cloud.py
- mani_skill_point_cloud_transformer.py
- mani_skill_state.py
- sac_mani_skill_state_1M_train.py
- mani_skill_point_cloud.py
- mani_skill_point_cloud_transformer.py
- mani_skill_state.py
- README.md
- README.md
- README.md
- __init__.py
- train_rl.py
- __init__.py
- builder.py
- env_utils.py
- evaluation.py
- observation_process.py
- parallel_runner.py
- replay_buffer.py
- rollout.py
- torch_parallel_runner.py
- wrappers.py
- __init__.py
- bc.py
- bcq.py
- cql.py
- td3_bc.py
- __init__.py
- sac.py
- td3.py
- __init__.py
- builder.py
- __init__.py
- mlp.py
- nn_utils.py
- pointnet.py
- transformer.py
- vae.py
- __init__.py
- deterministic.py
- gaussian.py
- __init__.py
- activation.py
- attention.py
- conv.py
- conv_module.py
- norm.py
- padding.py
- weight_init.py
- __init__.py
- continuous_policy.py
- vae_policy.py
- __init__.py
- continuous_value.py
- __init__.py
- builder.py
- utils.py
- __init__.py
- builder.py
- default_constructor.py
- __init__.py
- compression.py
- concat.py
- converter.py
- dict_array.py
- dict_utils.py
- filtering.py
- flatten.py
- list_utils.py
- padding.py
- shape_utils.py
- shuffle.py
- string_utils.py
- type.py
- wrapper.py
- __init__.py
- web_utils.py
- __init__.py
- base.py
- csv_handler.py
- pickle_handler.py
- __init__.py
- io.py
- utils.py
- __init__.py
- h5_utils.py
- hash_utils.py
- __init__.py
- split_array.py
- __init__.py
- collect_env.py
- config.py
- logger.py
- magic_utils.py
- module_utils.py
- path_utils.py
- process_utils.py
- random_utils.py
- registry.py
- timer.py
- __init__.py
- tensorboard_logger.py
- __init__.py
- checkpoint.py
- cuda_utils.py
- distributed_utils.py
- misc.py
- module_utils.py
- ops.py
- __init__.py
- __init__.py
- version.py
- build_docker.sh
- Dockerfile
- eval_bc_example.sh
- run_bc.sh
- run_bcq.sh
- run_cql.sh
- run_td3_bc.sh
- run_with_chunked_dataset.sh
- convert_state_to_pcd.sh
- eval_bc_example.sh
- run_bc.sh
- run_bcq.sh
- run_cql.sh
- run_td3_bc.sh
- run_with_chunked_dataset.sh
- run_SAC.sh
- environment.yml
- user_solution.py
- all_data_files.csv
- check_md5.py
- convert_state.py
- run_rl.py
- split_datasets.py
- baseline_results.png
- LICENSE
- README.md
- requirements.txt
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/haosulab/ManiSkill-Learn
Downloads the entire project code from GitHub to your computer.
cd ManiSkill-Learn
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
β οΈ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.
docker build -f scripts/docker/Dockerfile -t maniskill-learn .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 maniskill-learn
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
3. Python
EasyPrerequisites
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
python -m tools.run_rl configs/bc/mani_skill_point_cloud_transformer.py \
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)