Stone Tao

Yep this is the correct fix, I think it was there because we never used RRT in our examples. If you make a PR i can go and review/merge it

this depends on a task by task basis unfortunately. Robot proprioception data can be more easily normalized since there are joint limits. Other state data might not be easy to...

In terms of robot learning it works sufficiently fine to just use the state data as is. Propioceptive data tends to always be no larger than pi Tasks where state...

Closing this issue as it has gone stale. Feel free to reopen if not.

@xuanlinli17 can u find the MPC code from before without the missing dependencies? Also @Altriaex I'm aware ManiSkill2 is missing a bit in terms of example workflows (e.g. demo generation),...

Hi @Altriaex has this resolved your issue?

Those json config files are absolutely required for rendering @JankowskiChristopher, there is currently no way around it. I am a little confused why those json config files can't be added...

Unfortunately for some tasks the base_camera image is not sufficient and only one view might make the task too hard, even with depth information. I do not have baseline results...

Closing this issue as it has gone stale. Feel free to reopen if not.

Unfortunately vulkan is required for ManiSkill 2, although we are trying to remove that requirement in ManiSkill3 so you can just run state based (also means you can't render videos...