[RLlib; Offline RL] Added stop method to OfflineEnvRunner.
#47155
+59
−49
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
…ces in the buffer to disk. Signed-off-by: simonsays1980 <simon.zehnder@gmail.com>
Signed-off-by: simonsays1980 <simon.zehnder@gmail.com>
…'max_rows_per_file' is defining now the maximum number of episodes to store into a file/folder. Furthermore, unified buffer for episodes and column data. Signed-off-by: simonsays1980 <simon.zehnder@gmail.com>
simonsays1980
requested review from
sven1977 and
ArturNiederfahrenhorst
as code owners
sven1977
reviewed
Aug 15, 2024
| number of rows for the remaining samples could be | ||
| less than the defined maximum row number by the user. | ||
| """ | ||
| # If there are samples left over we have to write htem to disk. them |
There was a problem hiding this comment.
The parent method doesn't do anything, but I think we should still call it, what do you think?
super().stop()
sven1977
reviewed
Aug 15, 2024
| @@ -229,7 +239,7 @@ def _map_episodes_to_data(self, samples: List[EpisodeType]) -> None: | |||
| Columns.ACTIONS: pack_if_needed( | |||
| to_jsonable_if_needed(sample.get_actions(i), action_space) | |||
| ) | |||
| if Columns.OBS in self.output_compress_columns | |||
| if Columns.ACTIONS in self.output_compress_columns | |||
sven1977
reviewed
Aug 15, 2024
| self._samples = [] | ||
| else: | ||
| self._samples_data = [] | ||
| # Define the buffer for experiences stored until written to disk. |
There was a problem hiding this comment.
That was a little confusing :)
sven1977
approved these changes
Aug 15, 2024
There was a problem hiding this comment.
Love it. So much more elegant to put this in stop.
Just the nit about the parent stop method call.
Thanks @simonsays1980 !!
simonsays1980
changed the title
stop method to 'OfflineEnvRunner'
simonsays1980
changed the title
stop method to 'OfflineEnvRunner'stop method to OfflineEnvRunner.
sven1977
changed the title
stop method to OfflineEnvRunner.stop method to OfflineEnvRunner.
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.
Why are these changes needed?
The
max_rows_per_filegives a user control over the number of writing processes during a run when recording the experiences. It does so by buffering episodes or row data untilmax_rows_per_fileis reached.If the run stops, this buffer could be still non-empty. This PR proposes to override the
EnvRunner.stopmethod to write remaining episodes or step data onto disk.Related issue number
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.