Alexis DUBURCQ

I don't think it "works", even if in some cases it does. For example, this snippet hangs: ``` import nest_asyncio from requests_html import AsyncHTMLSession asession = AsyncHTMLSession() nest_asyncio.apply(asession.loop) async def...

I see what you mean, and I mostly agree, but in my view what you describe should be a higher level API than what `SubprocVectorEnv` is supposed to be. `SubprocVectorEnv`...

Ok, I got your point and I agree with you. But what about adding a `loss_fn` in the abstract base class for policies, that is basically doing nothing by default...

@Trinkle23897 Up !

No problem ! I can do it ! But what do you think about the idea ?

@Privilger I just wanted to let you know I developped a robotic simulator called [Jiminy](https://github.com/Wandercraft/jiminy) that is much faster, light weight, and easy to use than Gazebo. It is already...

@Trinkle23897 By the way, I would like to thank you for the amazing work that you did for Tianshou. In my opinion, it is by far the best framework for...

I don't think there is a need for multi-agent reinforcement learning at short term. To me the priority is to improve the current functionality. There is major flaws in the...

> I think it is independent with what you said. Of course it is! Work force being limited, someone working on a specific feature necessarily affects / slow-down the development...

How to handle the case where spatial force is not meaningful ? Two options: - [1] Return an exception if not implemented by default to make it optional. - [2]...