Antonin RAFFIN

Results 880 comments of Antonin RAFFIN

Thanks for the review =) > I'm only wondering why you would add this to the "Expenses" page and not to the "Balances" page? That's actually the main point of...

> However, since q_net_target parameters are updated using Polyak update, is there a reason why they are included in the optimizer? Would it be correct to use self.q_net.parameters() instead of...

> Hello, is there anything to modify in the check you mention in [test_cnn.py](https://github.com/DLR-RM/stable-baselines3/blob/4efee92fbad70f85aa094e27bd0a740274121795/tests/test_cnn.py#L195-L203) ? probably not indeed.

Hello, if you want to parallelize gradient steps, you need to have a look at https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/issues/11 and linked issues. if you want to parallelize data collection, you need to use...

> I have provided a minimal and working example to reproduce the bug hello please do not forget this step, that would allow us better to understand the problem and...

hello, thanks for the PR, but please keep it minimal (only update the env checker and the test related to it). Full graph support should be for another issue and...

Hello, could you please provide more information. Are you referring to https://github.com/DLR-RM/stable-baselines3/pull/1837 ?

> Is there a reason to do so? Simplicity. > Or is it just to save compute and does not effect the optimization process a lot? yes. They are mostly...

> If code there is, it is minimal and working Closing because the minimum requirements for seeking help are not met.

Hello, I'm not sure what you are trying to achieve, `evaluate_actions()` is used here: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/c070fc2faedaf28bf62299cc36c8be5ac68d15fd/sb3_contrib/ppo_recurrent/ppo_recurrent.py#L345-L350 So I would recommend to set a debugger and analyze the shape of the tensors...