Antonin RAFFIN
Antonin RAFFIN
> When passing these hyperparameters to the algorithm it does not work (remains at -200). I do not exactly understand why. You are missing the normalization wrapper: `envm = VecNormalize(envm,...
Hello, sorry for the late reply was on holidays... > Is that maybe exactly what you mention there? Yes > Regarding the duplicate tag (you are probably referring to issue...
> If you open a PR, I would be happy to contribute. Please do =) > By training multiple models simultaneously. Something like I was afraid of that answer... yes...
Hey, thanks for the PR =) I might wait until Huggingface PR is merged https://github.com/DLR-RM/rl-baselines3-zoo/pull/198 I will help @simoninithomas in the coming days.
Quickly looking at it, no additional tuning was in fact required?
Basic version is ready to review ;) https://github.com/DLR-RM/rl-baselines3-zoo/pull/250 An example: https://huggingface.co/sb3/ppo-MountainCarContinuous-v0
btw, this requires gym > 0.21, right?
Hello, I was more thinking about using the default hyperparams so you get for each env (already defined in the yaml files).
hello, you are probably searching for the `--env-kwargs` argument?
> to pass arguments to the environment used in training. I'm wanting to use a validation environment during training and am wondering either if I can pass arguments to the...