Open yilin-wu98 opened 2 years ago
I am afraid that if you want to accelerate the environments in robogym using envpool, you may have to translate the python code in robogym into c++ 🙃 But I think there are two things in envpool can make your life easier: we are now working on a private pool repo #155, which is a template repo to help customized environment integrated into envpool easier, another thing is that robotic manipulation tasks of dm_control #103 is in the todo list of envpool, please stay tuned :)
One more thing is that since you mentioned shadowhand manipulation task for parallel simulations, I highly recommend issac gym, if that suits your need.
Thanks for your reply! Regrading the private pool repo, is it public now or are you currently working on developing this repo?
We are still working on it, it is on the road map of envpool 0.7.0 release, hopefully :)
Motivation
We have a project that wants to have a large number of robotic manipulation environment in robogym in parallel to train a RL algorithm. I have taken a look at the docs and I know that for customized environment we need add C++ code and build from source following this guide. Also, so far in the existing added gym and dm_control environments, I haven't found any robotic arm or hand environment example. There are a lot of stuff to add in, including kinematics, different control modes, for a robotic manipulation environment if we start from C++ code and turn all the python code from robogym into C++. I am wondering if you have tested or considered adding support for robotic manipulation tasks. Do you have any suggestions on how to start to add in a complicated robotic manipulation tasks e.g., shadowhand manipulation?
Thanks for creating such a useful tool and codebase for parallel training in simulation!
Solution
Could you add some feature for easy transfer of other gym-based complicated robotic manipulation tasks into envpool? Or provide any guidance or suggestions on how to effectively build a customized robotic manipulation tasks into envpool besides what you had in the docs?
Additional context
Robogym: a repo developed by openai that has similar API as gym but includes more robotic manipulation tasks, e.g., shadowhand, etc. https://github.com/openai/robogym
Checklist