Reduce training time and improve expert loading code in the tutorials #810
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
The readthedocs pipeline failed due to timeouts when executing the cells of tutorial notebooks.
This was fixed by reducing the number of steps to train in the FAST mode of the AIRL tutorial.
Along the way I fixed the way experts are loaded in the tutorials:
Before: they were loaded based on normalized** environment names. However, the loader normalizes the names itself so it should be less confusing that we just load the experts based on the original environment name.
Also in one tutorial we were not even using the
load_expert
util function. I made sure it is used in all tutorials that load an expert in the same way.** normalized means slashes replaced by hyphens
Will fix #793 and fix #790
Testing
Changes are covered by the existing tests.