Computational framework for reinforcement learning in traffic control

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.

Official github page of UCF SST CitySim Dataset

Veins - The open source vehicular network simulation framework.

Sumo is a library that prepares for fast upload for iOS. It is effective when uploading by selecting images continuously.

We have used Deep Reinforcement Learning and Advanced Computer Vision techniques to for the creation of Smart Traffic Signals for Indian Roads. We have created the scripts for using SUMO as our environment for deploying all our RL models.

A multi-stack, ETSI compliant, V2X framework for ns-3.

Luxembourg SUMO Traffic (LuST) Scenario

SUMO tutorials from SUMO Quick Start and NetEdit to TraCI, CAVs, energy & emission, and SUMO2Unity.

Monaco SUMO Traffic (MoST) Scenario

A benchmark towards generalizable reinforcement learning for autonomous driving.

Toolbox for Map Conversion and Scenario Creation for Autonomous Vehicles.

applying multi-agent reinforcement learning for highway-merging autonomous vehicles

Adaptive real-time traffic light signal control system using Deep Multi-Agent Reinforcement Learning

Reinforcement Learning-based VANET simulations

Containerised SUMO. Use sumo, sumo-gui and TraCI with Docker. :whale: :car:

Reinforcement Learning + traffic microsimulation (via SUMO). Uses Ray RLLIB and forces SUMO into the OpenAI Gym Framework

Lane Changer Agent DQN

SUMO Pytorch Deep Reinforcement Learning Traffic Signal Control

Optimize traffic flow at intersections with a Deep Q-Learning agent. Utilizes reinforcement learning to control traffic signals efficiently.

An Activity-based Multi-modal Mobility Scenario Generator for SUMO. This project is available in the Eclipse SUMO contributed tools section (https://github.com/eclipse/sumo/tree/master/tools/contributed) under the name SAGA (SUMO Activity GenerAtion).

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

This project simulates deployment and migration of Service Function Chains (SFC) in data-centers.

We provide an open source software package for AV based simulation and testing running a docker container

No description provided.

Investigating Q-Learning and DQN variants for Traffic Signal Control problem

InTAS is the Ingolstadt traffic scenario for SUMO, which was designed, developed and validated with real traffic data from measuring points.

An environment-agnostic framework for comparing intersection control algorithms

Traffic Control Test Bed