# Gradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planning

arXiv: https://arxiv.org/abs/2604.00388 · HTML: https://mlsanity.com/paper/2604.00388/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [Wayformer: Motion Forecasting via Simple & Efficient Attention Networks](https://mlsanity.com/paper/2207.05844/) (2022)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving](https://mlsanity.com/paper/2303.05760/) (2023)
- [DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Driving](https://mlsanity.com/paper/2310.05885/) (2023)
- [Data-Centric Evolution in Autonomous Driving: A Comprehensive Survey of Big Data System, Data Mining, and Closed-Loop Technologies](https://mlsanity.com/paper/2401.12888/) (2024)
- [ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.02877/) (2024)
- [TAROT: Targeted Data Selection via Optimal Transport](https://mlsanity.com/paper/2412.00420/) (2024)
- [Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model](https://mlsanity.com/paper/2507.22615/) (2025)

## Abstract (arXiv)

We demonstrate that gradient-based data valuation produces curriculum orderings that significantly outperform metadata-based heuristics for training game-theoretic motion planners. Specifically, we apply TracIn gradient-similarity scoring to GameFormer on the nuPlan benchmark and construct a curriculum that weights training scenarios by their estimated contribution to validation loss reduction. Across three random seeds, the TracIn-weighted curriculum achieves a mean planning ADE of 1.704±0.029,m, significantly outperforming the metadata-based interaction-difficulty curriculum (1.822±0.014,m; paired t-test p=0.021, Cohen's dz=3.88) while exhibiting lower variance than the uniform baseline (1.772±0.134,m). Our analysis reveals that TracIn scores and scenario metadata are nearly orthogonal (Spearman ρ=-0.014), indicating that gradient-based valuation captures training dynamics invisible to hand-crafted features. We further show that gradient-based curriculum weighting succeeds where hard data selection fails: TracIn-curated 20% subsets degrade performance by 2×, whereas full-data curriculum weighting with the same scores yields the best results. These findings establish gradient-based data valuation as a practical tool for improving sample efficiency in game-theoretic planning.