Antonin RAFFIN

> I am curious which gSDE ingredient does exactly help. The consistent exploration. To solve this task, you need to build-up momentum, having a bang-bang like strategy is one way...

Hello, are you willing to implement and benchmark the algorithm?

> The algorithm is an Off-policy one. Is there any way or example to begin with this kind of algorithms? https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/pull/4 and please read https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/master/CONTRIBUTING.md

Hello, the traceback is not complete. I would suspect that the problem might come from Kaggle notebook, there is probably a timeout.

> I copied just the pertinent part of the log the traceback doesn't tell anything about why the process was terminated and nothing might relate it to SB3, it just...

Hello, this is indeed a known problem but it should not prevent you from using it at test time: it is only a `UserWarning` not an error. Or do you...

> Python file or kernel crashes a couple of seconds after UserWarning What is your PyTorch version? Could you try upgrading? > has stablebaselines3 version 1.8.0a4 and second machine has...

Oh, I see, looks like a problem with PyTorch between OS. Can you confirm that you have no problem in case you save and load on the same machine?

Hello, do you already have a live draft somewhere? apart from the rst format, what are the main issues with the current documentation according to you?

Hello, thanks for the suggestion, it is true that domain randomization is independent of the RL algorithm but in my mind, domain randomization is highly dependent on the environment, so...