# Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving

arXiv: https://arxiv.org/abs/2403.17805 · HTML: https://mlsanity.com/paper/2403.17805/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [PettingZoo: Gym for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2009.14471/) (2020)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Automatic Curriculum Learning For Deep RL: A Short Survey](https://mlsanity.com/paper/2003.04664/) (2020)
- [SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving](https://mlsanity.com/paper/2010.09776/) (2020)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective](https://mlsanity.com/paper/2202.02215/) (2022)
- [Scenic: A Language for Scenario Specification and Scene Generation](https://mlsanity.com/paper/1809.09310/) (2018)
- [Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning](https://mlsanity.com/paper/1911.04175/) (2019)
- [Scenic: A Language for Scenario Specification and Data Generation](https://mlsanity.com/paper/2010.06580/) (2020)
- [BARK: Open Behavior Benchmarking in Multi-Agent Environments](https://mlsanity.com/paper/2003.02604/) (2020)
- [Stabilizing Unsupervised Environment Design with a Learned Adversary](https://mlsanity.com/paper/2308.10797/) (2023)

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

- [Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities](https://mlsanity.com/paper/2408.12548/) (2024)
- [SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction](https://mlsanity.com/paper/2506.23316/) (2025)
- [Scaling Curriculum Learning For Autonomous Driving](https://mlsanity.com/paper/2608.22549/) (2026)

## Abstract (arXiv)

The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world application domains, such as autonomous driving, auto-curriculum generation is considered vital for obtaining robust and general policies. However, crafting traffic scenarios with multiple, heterogeneous agents is typically considered as a tedious and time-consuming task, especially in more complex simulation environments. In our work, we introduce MATS-Gym, a Multi-Agent Traffic Scenario framework to train agents in CARLA, a high-fidelity driving simulator. MATS-Gym is a multi-agent training framework for autonomous driving that uses partial scenario specifications to generate traffic scenarios with variable numbers of agents. This paper unifies various existing approaches to traffic scenario description into a single training framework and demonstrates how it can be integrated with techniques from unsupervised environment design to automate the generation of adaptive auto-curricula. The code is available at https://github.com/AutonomousDrivingExaminer/mats-gym.