Konstantin Ramthun

I think you can't implement all DR approaches in the environments alone. For e.g., Automatic Domain Randomization, you need additional evaluation episodes. Thus, I see DR more as an extension...

Do you have any updates on this? An option to specify the version of the inference server used in the package would be great.

Hi @dennisbader, thanks for your reply. Wouldn't it be possible to implement a one-hot encoder similar to the [CyclicTemporalEncoder](https://unit8co.github.io/darts/_modules/darts/dataprocessing/encoders/encoders.html#CyclicTemporalEncoder), using the `datetime_attribute_timeseries()` function? In this case the implementations of `accept_transformer()`...

Hi @dennisbader, thanks for the clarification. I’ll try to contribute to this, but I’ll need to see when I can get to it.

While implementing this feature, I noticed an inconsistency in the implementation of [datetime_attribute_timeseries](https://github.com/unit8co/darts/blob/8821f5109a59605f25a0a259c3f36ac31d094ac8/darts/utils/timeseries_generation.py#L574C1-L779C6) regarding datetime attributes with a variable maximum number of unique values, such as `day`, `dayofyear`, and `week`....

@dennisbader What do you think about the new options for encodings mentioned in (1) and (2)? The frequency awareness for one-hot encodings does not cover all possible frequencies, but I...

@dennisbader, what do you think about the proposed changes, especially making the encoders aware of a time series' frequency and start? Do you see any drawbacks to this approach?