tiny-differentiable-simulator VS procgen

I need differentiable rigid body dynamics because I want to do nonlinear MPC. One library that can do this is C++ is Tiny Differentiable Simulator https://github.com/erwincoumans/tiny-differentiable-simulator. As I understand it, this software uses a C++ auto-diff library and code generation to create CUDA kernels to compute fast derivatives in parallel. This seems pretty fast because it's C++. Another option is Brax https://github.com/google/brax. Brax uses JAX which I've never used, but from what I've seen online, JAX is popular for researchers and probably very good.

https://github.com/google-research/tiny-differentiable-simul...

Yes, Chrome about://tracing is great to visualize your custom timing data. Happy used for the last 5 years in Bullet and recent physics engines, including events across tracing multiple threads:

https://github.com/google-research/tiny-differentiable-simul...

Or our C++ and CUDA Tiny Differentiable Simulator: https://github.com/google-research/tiny-differentiable-simulator

Drake (and also tiny-differentiable-simulator that I know of) are using meshcat and it seems neat to me

Is there a single-task, multi-scene environment using continuous action spaces? Single-task and multi-scene envs are similar to gym-super-mario-bros and CoinRun in procgen .But they are all discrete action spaces. Thank you!!!!!

And now "bigfish" from the procgen Gym environments, tested on Stable Baselines 3. (No success)

It's not exactly a tutorial, but OpenSpiel has C++ environments ported to Python that are relatively simple and easy to understand. Procgen would be a more complicated reference to check out as well.