# Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward

arXiv: https://arxiv.org/abs/2112.06185 · HTML: https://mlsanity.com/paper/2112.06185/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 12 Dec 2021.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Adversarial Policies: Attacking Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10615/) (2019)
- [The ApolloScape Open Dataset for Autonomous Driving and its Application](https://mlsanity.com/paper/1803.06184/) (2018)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [On a Formal Model of Safe and Scalable Self-driving Cars](https://mlsanity.com/paper/1708.06374/) (2017)
- [SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving](https://mlsanity.com/paper/2010.09776/) (2020)
- [Certified Adversarial Robustness for Deep Reinforcement Learning](https://mlsanity.com/paper/1910.12908/) (2019)
- [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)
- [Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies](https://mlsanity.com/paper/2002.12078/) (2020)
- [Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles](https://mlsanity.com/paper/1806.01368/) (2018)
- [Driving-Policy Adaptive Safeguard for Autonomous Vehicles Using Reinforcement Learning](https://mlsanity.com/paper/2012.01010/) (2020)

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

- [Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers](https://mlsanity.com/paper/2405.12424/) (2024)

## Abstract (arXiv)

Discovering hazardous scenarios is crucial in testing and further improving driving policies. However, conducting efficient driving policy testing faces two key challenges. On the one hand, the probability of naturally encountering hazardous scenarios is low when testing a well-trained autonomous driving strategy. Thus, discovering these scenarios by purely real-world road testing is extremely costly. On the other hand, a proper determination of accident responsibility is necessary for this task. Collecting scenarios with wrong-attributed responsibilities will lead to an overly conservative autonomous driving strategy. To be more specific, we aim to discover hazardous scenarios that are autonomous-vehicle responsible (AV-responsible), i.e., the vulnerabilities of the under-test driving policy. To this end, this work proposes a Safety Test framework by finding Av-Responsible Scenarios (STARS) based on multi-agent reinforcement learning. STARS guides other traffic participants to produce Av-Responsible Scenarios and make the under-test driving policy misbehave via introducing Hazard Arbitration Reward (HAR). HAR enables our framework to discover diverse, complex, and AV-responsible hazardous scenarios. Experimental results against four different driving policies in three environments demonstrate that STARS can effectively discover AV-responsible hazardous scenarios. These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.