# Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving

arXiv: https://arxiv.org/abs/2309.14235 · HTML: https://mlsanity.com/paper/2309.14235/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Placed in

- End-to-end autonomous driving / [Adversarial scenarios and safety testing](https://mlsanity.com/driving/adversarial-scenarios-and-safety-testing/)

## Builds on (most cited first, 25 of 25)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems](https://mlsanity.com/paper/1810.05642/) (2018)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior](https://mlsanity.com/paper/2112.05077/) (2021)
- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions](https://mlsanity.com/paper/2003.08536/) (2020)
- [A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective](https://mlsanity.com/paper/2202.02215/) (2022)
- [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022)
- [Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation](https://mlsanity.com/paper/1811.00145/) (2018)
- [Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method](https://mlsanity.com/paper/2003.01197/) (2020)
- [Model-Free Renewable Scenario Generation Using Generative Adversarial Networks](https://mlsanity.com/paper/1707.09676/) (2017)
- [Accelerated Evaluation of Automated Vehicles Safety in Lane Change Scenarios Based on Importance Sampling Techniques](https://mlsanity.com/paper/1605.04965/) (2016)
- [Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving](https://mlsanity.com/paper/1903.10654/) (2019)
- [Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability](https://mlsanity.com/paper/2209.08025/) (2022)
- [Convergence of Learning Dynamics in Stackelberg Games](https://mlsanity.com/paper/1906.01217/) (2019)
- [Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training](https://mlsanity.com/paper/2202.09514/) (2022)
- [Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles](https://mlsanity.com/paper/2102.03483/) (2021)
- [Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms](https://mlsanity.com/paper/2109.12286/) (2021)
- [DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning](https://mlsanity.com/paper/2107.11762/) (2021)
- [(Re)2H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learning](https://mlsanity.com/paper/2302.13726/) (2023)

## Built on by (most cited first, 3 of 3)

- [VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness](https://mlsanity.com/paper/2601.12672/) (2026)
- [Dynamically Expanding Capacity of Autonomous Driving with Near-Miss Focused Training Framework](https://mlsanity.com/paper/2406.02865/) (2024)
- [3CSim: CARLA Corner Case Simulation for Control Assessment in Autonomous Driving](https://mlsanity.com/paper/2409.10524/) (2024)

## Abstract (arXiv)

The deployment of autonomous vehicles (AVs) has faced hurdles due to the dominance of rare but critical corner cases within the long-tail distribution of driving scenarios, which negatively affects their overall performance. To address this challenge, adversarial generation methods have emerged as a class of efficient approaches to synthesize safety-critical scenarios for AV testing. However, these generated scenarios are often underutilized for AV training, resulting in the potential for continual AV policy improvement remaining untapped, along with a deficiency in the closed-loop design needed to achieve it. Therefore, we tailor the Stackelberg Driver Model (SDM) to accurately characterize the hierarchical nature of vehicle interaction dynamics, facilitating iterative improvement by engaging background vehicles (BVs) and AV in a sequential game-like interaction paradigm. With AV acting as the leader and BVs as followers, this leader-follower modeling ensures that AV would consistently refine its policy, always taking into account the additional information that BVs play the best response to challenge AV. Extensive experiments have shown that our algorithm exhibits superior performance compared to several baselines especially in higher dimensional scenarios, leading to substantial advancements in AV capabilities while continually generating progressively challenging scenarios. Code is available at https://github.com/BlueCat-de/SDM.