beam-search implementation for more exhausting sampling #35
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
verdimrc
reviewed
May 4, 2023
Hopefully this fixes failing tests
Coverage Report
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
added 3 commits
May 4, 2023 11:03
verdimrc
reviewed
May 4, 2023
verdimrc
approved these changes
May 4, 2023
|
Thank you @laurcate , @patrick22414. Feel free to merge to main. Ignore the linter error -- looks like a newer Black wants to reformat even files outside this PR. Recommend you to review the missing coverage in your new function (see the coverage report a few comments above). I'm okay if you want to add extra tests for the edge cases as a separate PR. |
|
Thank you for the additional test cases. |
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Outdated suggestions cannot be applied.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.
Issue #, if available:
Description of changes:
this function largely replaces A2RL Simulator.gpt_sample_n_steps(). It does not
concern states/actions/rewards and only generates the next N tokens using beam search.
This function is to be used by a BYO planner downstream as a replacement of the normal sampling strategy.
Additionally a notebook with example of implementaiton has been added.
Testing done:
Yes
Merge Checklist
Put an
xin the boxes that apply. You can also fill these out after creating the PR. If you'reunsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of
what we are going to look for before merging your pull request.
By submitting this pull request, I confirm that my contribution is made under the terms of the
Apache 2.0 license.