# Behaviorally Diverse Traffic Simulation via Reinforcement Learning

arXiv: https://arxiv.org/abs/2011.05741 · HTML: https://mlsanity.com/paper/2011.05741/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [Data-driven Traffic Simulation: A Comprehensive Review](https://mlsanity.com/paper/2310.15975/) (2023)
- [Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Driving](https://mlsanity.com/paper/2311.11056/) (2023)
- [TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving](https://mlsanity.com/paper/2203.16792/) (2022)
- [Text-to-Drive: Diverse Driving Behavior Synthesis via Large Language Models](https://mlsanity.com/paper/2406.04300/) (2024)
- [(Re)2H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learning](https://mlsanity.com/paper/2302.13726/) (2023)
- [Blending Data-Driven Priors in Dynamic Games](https://mlsanity.com/paper/2402.14174/) (2024)
- [Adversarial and Reactive Traffic Entities for Behavior-Realistic Driving Simulation: A Review](https://mlsanity.com/paper/2409.14196/) (2024)
- [Analyzing Closed-loop Training Techniques for Realistic Traffic Agent Models in Autonomous Highway Driving Simulations](https://mlsanity.com/paper/2410.15987/) (2024)
- [EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial Representations](https://mlsanity.com/paper/2504.05422/) (2025)
- [NashFormer: Leveraging Local Nash Equilibria for Semantically Diverse Trajectory Prediction](https://mlsanity.com/paper/2305.17600/) (2023)
- [PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving Simulation](https://mlsanity.com/paper/2606.12616/) (2026)

## Abstract (arXiv)

Traffic simulators are important tools in autonomous driving development. While continuous progress has been made to provide developers more options for modeling various traffic participants, tuning these models to increase their behavioral diversity while maintaining quality is often very challenging. This paper introduces an easily-tunable policy generation algorithm for autonomous driving agents. The proposed algorithm balances diversity and driving skills by leveraging the representation and exploration abilities of deep reinforcement learning via a distinct policy set selector. Moreover, we present an algorithm utilizing intrinsic rewards to widen behavioral differences in the training. To provide quantitative assessments, we develop two trajectory-based evaluation metrics which measure the differences among policies and behavioral coverage. We experimentally show the effectiveness of our methods on several challenging intersection scenes.