human demo collection during online interaction #1444
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
tomsilver
commented
Mar 29, 2023
| @@ -29,7 +29,6 @@ def test_online_nsrt_learning_approach(): | |||
| "num_test_tasks": 3, | |||
| "explorer": "random_options", | |||
| "online_learning_max_novelty_count": float("inf"), | |||
| "online_learning_lifelong": True | |||
There was a problem hiding this comment.
i'm removing this because I think there's a separate bug: #1445
| @@ -909,6 +909,9 @@ def copy(self) -> State: | |||
| class LoggingMonitor(abc.ABC): | |||
| """Observes states and actions during environment interaction.""" | |||
|
|
|||
| def reset(self, train_or_test: str, task_idx: int) -> None: | |||
| """Called when the monitor starts a new episode.""" | |||
|
|
|||
There was a problem hiding this comment.
did we really mean to do nothing here? If so, could you leave a comment explaining why and also use a pass statement?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
this is hacky, but addressing root issues (#1443) will require a lot more work. a better way to implement this would be to have the teacher and the student interacting in the same environment. that's certainly what we will want to do in the real world.
I tested this through the online bridge policy learning branch.