Dreamer-V2

[belerico]

Summary

This PR introduce the Dreamer-V2 algorithm from https://arxiv.org/abs/2010.02193

Type of Change

Please select the one relevant option below:

• New feature (non-breaking change that adds functionality)

Checklist

Please confirm that the following tasks have been completed:

• [x] I have tested my changes locally and they work as expected. (Please describe the tests you performed.)
• [x] I have added unit tests for my changes, or updated existing tests if necessary.
• [x] I have updated the documentation, if applicable.
• [x] I have installed pre-commit and run locally for my code changes.

Screenshots or Visuals (Optional)

If applicable, please provide screenshots, diagrams, graphs, or videos of the changes, features or the error.

Additional Information (Optional)

Those are the training loss and rewards con DMC Walker-Walk with the standard hyperparameters found in dreamer_v2/args.py

Thank you for your contribution! Once you have filled out this template, please ensure that you have assigned the appropriate reviewers and that all tests have passed.

[belerico]

Maybe it's better to account for the action repeat as we have done in Dreamer-V1 @michele-milesi