mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning

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.

Source: arXiv:2601.22074v1 - http://arxiv.org/abs/2601.22074v1 PDF: https://arxiv.org/pdf/2601.22074v1 Original Link: http://arxiv.org/abs/2601.22074v1