feat(eval): Integrate ResAD with toy waypoint environment for ADE/FDE metrics#134
Open
Capri2014 wants to merge 2 commits into
Open
feat(eval): Integrate ResAD with toy waypoint environment for ADE/FDE metrics#134Capri2014 wants to merge 2 commits into
Capri2014 wants to merge 2 commits into
Conversation
- Track policy_entropy in eval metrics for exploration quality - Save best_entropy.pt when entropy reaches new best - Record entropy_history.json with episode-wise records - Enhance train_metrics.json with best_checkpoint section - Higher entropy = more exploration = better RL generalization Daily pipeline PR #1 (2026-02-18)
… metrics - Add ResAD policy wrapper (policy_resad) for toy environment - Add create_resad_policy() factory function for checkpoint loading - Update eval_toy_waypoint_env.py with ADE/FDE metrics computation - Add comparison mode (--policy compare) for SFT vs RL vs ResAD - Fix ResAD tensor dimension handling for 2D features - Compute summary statistics with mean/std for all metrics Usage: python -m training.rl.eval_toy_waypoint_env --policy sft --episodes 20 python -m training.rl.eval_toy_waypoint_env --policy resad --checkpoint resad.pt python -m training.rl.eval_toy_waypoint_env --policy compare --episodes 50 Output: out/eval/<run_id>/metrics.json with ADE/FDE summary metrics
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull Request Template
Summary
Brief description of what changed (1-2 sentences).
Changes
Testing
Checklist
mainbranchRelated PRs/Issues
Link to related PRs or issues.
Note: This repository uses squash merging. All commits will be collapsed into one.