Antonin RAFFIN

> Will these methods work with all_plots.py as well? I just wanted to make sure for plotting training and evaluation. For evaluation, you will need to merge the `evaluations.npz` files....

> made a Google Colab notebook to perform this task. could you share the link as it might be useful for others? > it appears evaluations.npz is a dictionary where...

> For evaluations.npz, is there a way to get all the keys? `.keys()`?

> What are the differences between these model files? one is a checkpoint, this other is saved at the end of training, the last one is the best model according...

> Sorry, what more information is needed? The hyperparameters used and your system/lib information (os, gym version, mujoco version, sb3 version, ...)

Hello, TPE is already kind of doing bayesian optimization, no? (predict the outcome for a given set of parameters and provide uncertainy). GP is already available here: https://github.com/DLR-RM/rl-baselines3-zoo/blob/master/rl_zoo3/exp_manager.py#L685-L691 > In...

> I am happy with implementing BOTorch here as I am going to perform a just to be sure, you plan to use https://optuna.readthedocs.io/en/stable/reference/generated/optuna.integration.BoTorchSampler.html, right?

Hello, > s, is there an option to smooth them like one could when plotting the training curves through a rolling window? There is no option currently, but normally for...

Hello, > can potentially help improve training stability in DRL do you have experimental results to back this claim? In the [paper](http://www.gatsby.ucl.ac.uk/~balaji/udl-camera-ready/UDL-24.pdf) linked in the blog post, results are on...

> PandaPush-v1 TQC: @qgallouedec could you share the runs and the command line you use? (so it's easier for @fikricanozgur to reproduce runs) maybe would be good to move the...