feat: difficulty based curriculum sampling strategy#428
Open
RUFFY-369 wants to merge 5 commits intoNousResearch:mainfrom
Open
feat: difficulty based curriculum sampling strategy#428RUFFY-369 wants to merge 5 commits intoNousResearch:mainfrom
RUFFY-369 wants to merge 5 commits intoNousResearch:mainfrom
Conversation
Add CurriculumScheduler to atroposlib/envs/ with: - EMA-based per-item difficulty tracking from reward signals - Quantile-based difficulty binning (configurable N bins) - Three sampling strategies: uniform, easy_first, competence_based - Competence-based strategy cites Platanios et al. 2019 - Opt-in integration in BaseEnv via 3 config fields - WandB metrics for difficulty distribution tracking - Checkpoint save/load support 22/22 tests passing.
for more information, see https://pre-commit.ci
This was referenced Mar 30, 2026
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Type
📝 General Information
Description
Implemented an Easy-First
CurriculumSchedulerto help with sample efficiency in complex tasks. It maps training items to difficulty bins and shifts the sampling distribution as the model hits "competence" thresholds.I added three main strategies:
easy_first,hard_first, andweighted_uniform. The goal is to let the model master the basics before the pipeline introduces high-difficulty edge cases.Related Issues
Type of Change
✅ Developer & Reviewer Checklist