{"id":49571038,"url":"https://github.com/mujocolab/mjlab_playground","last_synced_at":"2026-05-03T14:03:02.624Z","repository":{"id":349236647,"uuid":"1200043674","full_name":"mujocolab/mjlab_playground","owner":"mujocolab","description":"A collection of tasks built on mjlab","archived":false,"fork":false,"pushed_at":"2026-04-15T06:34:29.000Z","size":7931,"stargazers_count":69,"open_issues_count":1,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-15T07:30:47.817Z","etag":null,"topics":["humanoid","mjlab","mujoco","quadruped","reinforcement-learning","robotics","sim2real"],"latest_commit_sha":null,"homepage":"https://mujocolab.github.io/mjlab","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mujocolab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-03T01:23:22.000Z","updated_at":"2026-04-15T06:50:21.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/mujocolab/mjlab_playground","commit_stats":null,"previous_names":["mujocolab/mjlab_playground"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mujocolab/mjlab_playground","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mujocolab%2Fmjlab_playground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mujocolab%2Fmjlab_playground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mujocolab%2Fmjlab_playground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mujocolab%2Fmjlab_playground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mujocolab","download_url":"https://codeload.github.com/mujocolab/mjlab_playground/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mujocolab%2Fmjlab_playground/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32571456,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T06:36:36.687Z","status":"ssl_error","status_checked_at":"2026-05-03T06:36:09.306Z","response_time":103,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["humanoid","mjlab","mujoco","quadruped","reinforcement-learning","robotics","sim2real"],"created_at":"2026-05-03T14:03:01.977Z","updated_at":"2026-05-03T14:03:02.617Z","avatar_url":"https://github.com/mujocolab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# mjlab playground\n\nA collection of tasks built with [mjlab](https://github.com/mujocolab/mjlab), starting with ports from [MuJoCo Playground](https://playground.mujoco.org/).\n\n## Tasks\n\n| Task ID | Robot | Description | Preview |\n|---------|-------|-------------|---------|\n| **Getup** | | | |\n| `Mjlab-Getup-Flat-Unitree-Go1` | Unitree Go1 | Fall recovery on flat terrain | \u003cimg src=\"https://raw.githubusercontent.com/mujocolab/mjlab_playground/assets/go1_getup_teaser.gif\" width=\"200\"/\u003e |\n| `Mjlab-Getup-Flat-Booster-T1` | Booster T1 | Fall recovery on flat terrain | \u003cimg src=\"https://raw.githubusercontent.com/mujocolab/mjlab_playground/assets/t1_getup_teaser.gif\" width=\"200\"/\u003e |\n\n## Getting Started\n\n```bash\ngit clone https://github.com/mujocolab/mjlab_playground.git \u0026\u0026 cd mjlab_playground\nuv sync\n```\n\nTrain a task:\n\n```bash\nuv run train \u003ctask-id\u003e --num_envs 4096\n```\n\nPlay back a trained policy:\n\n```bash\nuv run play \u003ctask-id\u003e\n```\n\n### Getup training\n\nOn a single NVIDIA 5090, the Go1 getup task converges in ~2 minutes and T1 in ~8 minutes, but we continue training with a curriculum that progressively tightens action rate, joint velocity, and power penalties to produce smoother, safer policies.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/mujocolab/mjlab_playground/assets/training_curves.png\" width=\"80%\"/\u003e\n\u003c/p\u003e\n\n## Citation\n\nIf you use this repository in your research, consider citing mjlab:\n\n```bibtex\n@misc{zakka2026mjlablightweightframeworkgpuaccelerated,\n  title={mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning},\n  author={Kevin Zakka and Qiayuan Liao and Brent Yi and Louis Le Lay and Koushil Sreenath and Pieter Abbeel},\n  year={2026},\n  eprint={2601.22074},\n  archivePrefix={arXiv},\n  primaryClass={cs.RO},\n  url={https://arxiv.org/abs/2601.22074},\n}\n```\n\n## License\n\nThis repository is released under an [Apache-2.0 License](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmujocolab%2Fmjlab_playground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmujocolab%2Fmjlab_playground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmujocolab%2Fmjlab_playground/lists"}