Add new metrics

[paul-buerkner]

This PR is just to start the discussion on new metrics (beyond MMD). I have implemented the RMSE and would like you, @LarsKue, to check if the code structure generally looks reasonable.

Additional questions:

• For MMD, the number of samples (2nd dimension in the tensor?) does not need to be the same for both tensors. For RMSE the number of samples needs to be the same. How do we safely enforce this?
• What is the best way to normalize the RMSE? There are different ways to do it (e.g., https://www.marinedatascience.co/blog/2019/01/07/normalizing-the-rmse/). What is typtically considered in our context?

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

Attention: Patch coverage is 65.00000% with 7 lines in your changes missing coverage. Please review.

Project coverage is 52.16%. Comparing base (5dc599e) to head (e97966c).

Files with missing lines	Patch %	Lines
...flow/metrics/functional/root_mean_squared_error.py	44.44%	5 Missing ⚠️
bayesflow/metrics/root_mean_squard_error.py	71.42%	2 Missing ⚠️

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@            Coverage Diff             @@
##              dev     #194      +/-   ##
==========================================
+ Coverage   52.10%   52.16%   +0.06%     
==========================================
  Files         140      142       +2     
  Lines        3190     3209      +19     
==========================================
+ Hits         1662     1674      +12     
- Misses       1528     1535       +7     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[LarsKue]

LGTM!