MuJoCo derived Simulator for High Fidelity Vision RL training natively on GPU [D]

Hi everyone, For the past couple of weeks I have been working on a simulator project considering the shortcomings of MuJoCo. There are things that people like and also don't like about MuJoCo, like the CPU dependency on MuJoCo which makes the simulation not parallelizable beyond a certain limit (depending on the hardware). I know there exists MJX which is GPU accelerated, however, it is not really made for vision based RL pipelines and training. There is also NVIDIA Isaac ecosystem, but that requires a powe