# RDAR: Reward-Driven Agent Relevance Estimation for Autonomous Driving

arXiv: https://arxiv.org/abs/2509.19789 · HTML: https://mlsanity.com/paper/2509.19789/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement](https://mlsanity.com/paper/1903.06059/) (2019)
- [Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research](https://mlsanity.com/paper/2310.08710/) (2023)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Robust Autonomy Emerges from Self-Play](https://mlsanity.com/paper/2502.03349/) (2025)
- [Identifying Driver Interactions via Conditional Behavior Prediction](https://mlsanity.com/paper/2104.09959/) (2021)
- [DriveGPT: Scaling Autoregressive Behavior Models for Driving](https://mlsanity.com/paper/2412.14415/) (2024)
- [AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution](https://mlsanity.com/paper/2411.15102/) (2024)
- [Scaling Laws of Motion Forecasting and Planning -- Technical Report](https://mlsanity.com/paper/2506.08228/) (2025)
- [Agent Prioritization for Autonomous Navigation](https://mlsanity.com/paper/1909.08792/) (2019)
- [Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning](https://mlsanity.com/paper/2312.15122/) (2023)

## Built on by (most cited first, 1 of 1)

- [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026)

## Abstract (arXiv)

Human drivers focus only on a handful of agents at any one time. On the other hand, autonomous driving systems process complex scenes with numerous agents, regardless of whether they are pedestrians on a crosswalk or vehicles parked on the side of the road. While attention mechanisms offer an implicit way to reduce the input to the elements that affect decisions, existing attention mechanisms for capturing agent interactions are quadratic, and generally computationally expensive. We propose RDAR, a strategy to learn per-agent relevance -- how much each agent influences the behavior of the controlled vehicle -- by identifying which agents can be excluded from the input to a pre-trained behavior model. We formulate the masking procedure as a Markov Decision Process where the action consists of a binary mask indicating agent selection. We evaluate RDAR on a large-scale driving dataset, and demonstrate its ability to learn an accurate numerical measure of relevance by achieving comparable driving performance, in terms of overall progress, safety and performance, while processing significantly fewer agents compared to a state of the art behavior model.