Vikash Kumar

IIRC it was upside down in MuJoCo_py. So it might be a stale rationale that needs an update for new official wrappers. [This is the line](https://github.com/vikashplus/robohive/blob/main/robohive/renderer/mj_renderer.py#L117) where it happens. Feel...

@shivakanthsujit -- mered into `dev`. It will go out with the next release.

@tattrongvu -- The latest version of `FrankaKitchen` environments is `v4`. - Please see [here](https://github.com/vikashplus/robohive/blob/main/robohive/envs/multi_task/substeps1/franka_kitchen.py#L292-L368) for the latest version of these environments. - you can also follow the [change log](https://github.com/vikashplus/robohive/tree/main/robohive/envs/multi_task) to...

1. You can render camera views from an env and random policy with ``` python utils/examine_env.py --env_name FK1_MicroOpenRandom-v4 --num_episodes 1 --camera_name top_cam --render offscreen ``` 2. Rending speed depends on...

Hi Christos, Thanks for your interest in RoboHive. All RoboHive environments at its core are vanilla gym environments. So I don't think you need anything more than `import robohive` to...

Try the `dev` branch. It uses the official mujoco bindings by default. Hopefull that will fix this issue.

This seems like an error coming from policy initialization from Ray and SAC side. I haven't used them so it's a bit hard for me to pinpoint. If I have...

RoboHive currently supports [action normalization](https://github.com/vikashplus/robohive/blob/main/robohive/envs/env_base.py#L71C16-L71C29) (can be configured during registration) but doesn't support any observation normalization, or observation precision. The rationale is that observations are usually quite heterogenous (linear, angular,...

The env-API/ MDP definitions are designed to abstract out the physical meaning to promote generalization in data-driven methods. However, it's still possible to peel the layer and understand these variables....

Thank you for your effort with the Ray Integration. It's going to be a big win. Keep me in the loop as you make progress.