fikricanozgur

I have the exact problem. Did you solve it?

What's the status with this PR?

Hello, I would appreciate if you could give your comment on this question when you find the time. If you do not support this kind of inquires then kindly let...

Alright, thanks for looking into it. I will check the hyperparameters again and see if I can reproduce your results.

Yes, that is rather surprising to me as well. I am working on a project and using SB3 for trainings, it might be that I changed something in the code...

I also ran some tests and you can see them [here](https://wandb.ai/fikricanozgur/zoo3-push-fresh-installation?workspace=user-fikricanozgur). In summary, I trained 8 agents for PandaPush-v1 with TQC where 4 of them were trained using the default...

L2 regularization on the weights (using AdamW) with gSDE seem to solve the divergent behavior observed previously. Thanks @araffin. 

Hi, I used the TQC algorithm with the default hyperparameters in the repo and turned gSDE on. I changed the optimizer to AdamW using its default weight decay of 0.01....