[RLlib; Offline RL] Add configuration parameter ignore_final_observation and automatic episode ID generation.#52107
Merged
sven1977 merged 5 commits intoray-project:masterfrom Apr 9, 2025
Conversation
… final observations to zero. Furthermore added a test for this parameter. In addition added an automatic episode ID generation in '_map_to_episodes' in 'OfflinePreLearner'. Signed-off-by: simonsays1980 <simon.zehnder@gmail.com>
Signed-off-by: simonsays1980 <simon.zehnder@gmail.com>
sven1977
reviewed
Apr 9, 2025
Signed-off-by: Sven Mika <sven@anyscale.io>
sven1977
approved these changes
Apr 9, 2025
Contributor
sven1977
left a comment
There was a problem hiding this comment.
LGTM! Thanks for this simplification enhancement @simonsays1980 !
han-steve
pushed a commit
to han-steve/ray
that referenced
this pull request
Apr 11, 2025
…tion` and automatic episode ID generation. (ray-project#52107) Signed-off-by: Steve Han <stevehan2001@gmail.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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?
Users who run simple behavior cloning on their data need to provide a next state in
Columns.NEXT_OBSof their data set. Because the next state is not used in BC many users might not have this. This PR proposes a new parameterignore_final_observationin offline settings to set last states by default to zero.In addition this PR adds an automatic ID generation if
Columns.EPS_IDcannot be found in the schema.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.