rl
rl copied to clipboard
[Refactor] Dreamer v1 refactor
Description
Draft PR to facilitate discussion:
The proposed change extracts training steps in wrappers to reduce length of the example, but as there few control logging parameters needed, it creates nasty large function signatures, which are split multi-line by µfmt and do not really achieve the goal IMHO. (If such change would be accepted, the wrappers can be clearly moved to utils or models file.)
@vmoens @BY571
Motivation and Context
Discuss ideas for refactoring Dreamer V1.
Types of changes
Refactor
Checklist
Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!
- [ ] I have read the CONTRIBUTION guide (required)
- [ ] My change requires a change to the documentation.
- [ ] I have updated the tests accordingly (required for a bug fix or a new feature).
- [ ] I have updated the documentation accordingly.