Antonin RAFFIN

> Also I tried looking with grep for awhile and the only place where the debug mode is even used is here in short: - `verbose=0`: no output, when users...

Hello, Thanks for the proposal. Correct me if I'm wrong but intrinsic rewards are simply added (with some scale factor) to the reward of the environment? In that case, providing...

closing as outside the scope of SB3

Hello, thanks for reporting the issue. I also thought the batch norm stats where included in the parameters, but actually no... See https://discuss.pytorch.org/t/batch-norm-parameters-not-included-in-model-parameters/10265/2 the idea behind is that batch norm...

Note: one fast way to retrieve all batch norm params is like that: ```python # Include both online net and target, need to be filtered to each separately batch_norm_params =...

> I trained a model in version 1.2 and then tried to load it in 1.4. I am not perfectly sure if this is the cause of the error though....

Hello, what were you trying to log? (a minimal code to reproduce the issue would be appreciated ;)) PS: Please open an issue first next time (as mentioned in our...

Hello, rather than changing the install behavior, I would be more in favor of making SB3 run without `pandas` and `matplotlib`, so when you install it with `pip install --no-deps`...

> generates several monitor files (in my case, 3). Why is that? I That's normal, one per environment to avoid any race condition (as in https://github.com/DLR-RM/stable-baselines3/issues/647). > In other words,...

Hello, the feature request seems reasonable, however: - I consider it low priority so I would welcome PR from the community for that (maybe you want to do it?) -...