mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910032410443776 |
|---|---|
| author | Zakka, Kevin Liao, Qiayuan Yi, Brent Lay, Louis Le Sreenath, Koushil Abbeel, Pieter |
| author_facet | Zakka, Kevin Liao, Qiayuan Yi, Brent Lay, Louis Le Sreenath, Koushil Abbeel, Pieter |
| contents | We present mjlab, a lightweight, open-source framework for robot learning that combines GPU-accelerated simulation with composable environments and minimal setup friction. mjlab adopts the manager-based API introduced by Isaac Lab, where users compose modular building blocks for observations, rewards, and events, and pairs it with MuJoCo Warp for GPU-accelerated physics. The result is a framework installable with a single command, requiring minimal dependencies, and providing direct access to native MuJoCo data structures. mjlab ships with reference implementations of velocity tracking, motion imitation, and manipulation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22074 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning Zakka, Kevin Liao, Qiayuan Yi, Brent Lay, Louis Le Sreenath, Koushil Abbeel, Pieter Robotics We present mjlab, a lightweight, open-source framework for robot learning that combines GPU-accelerated simulation with composable environments and minimal setup friction. mjlab adopts the manager-based API introduced by Isaac Lab, where users compose modular building blocks for observations, rewards, and events, and pairs it with MuJoCo Warp for GPU-accelerated physics. The result is a framework installable with a single command, requiring minimal dependencies, and providing direct access to native MuJoCo data structures. mjlab ships with reference implementations of velocity tracking, motion imitation, and manipulation tasks. |
| title | mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2601.22074 |