mjlab combines Isaac Lab's proven API with best-in-class MuJoCo physics to provide lightweight, modular abstractions for RL robotics research and sim-to-real deployment.

Or at least it will, once I finish the slow process of documenting everything ...

We propose TraceRL, a trajectory-aware reinforcement learning method for diffusion language models, which demonstrates the best performance among RL approaches for DLMs. We also introduce a ...