Popular GitHub Repositories for Traffic Simulation

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR 2025.

TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction. ICRA 2023. You may also want to check out the updated version: https://github.com/zhejz/TrafficBotsV1.5

TrafficBots V1.5: TrafficBots + HPTR. 3rd place solution for Waymo Open Sim Agent Challenge 2024.

We propose a driver modeling process of an intelligent autonomous driving policy, which is obtained through Q-learning.

A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

RouteRL is a multi-agent reinforcement learning framework for modeling and simulating the collective route choices of humans and autonomous vehicles.

Website for the ECC 2022 paper titled "Learning Eco-Driving Strategies at Signalized Intersections"

AGADE Traffic is an agent based traffic simulator written in Java. For more information visit our website.

Supervised and Reinforcement Learning Traffic Simulation Model

Reinforcement Learning for Traffic Signal Optimization. We significantly reduce travel time compared to existing signal timing methods by training RL agents with omnipresent induction sensor data.

Linux Build for training of traffic signal project on Colab

In this repository, all codes necessary to implement an optimised traffic simulation are presented. This includes a one single intersection layout, and two intserection with one agent and multiagent.