rChimisso/2WSI-RL
Study on the application of reinforcement learning to the management of a traffic light intersection.
This project compares different traffic light management strategies to reduce congestion. It takes in real-world traffic patterns, simulates them, and then outputs performance metrics for fixed-cycle lights versus two types of AI-controlled lights (Q-Learning and Deep Q-Learning). Traffic engineers, urban planners, and smart city designers can use this to understand how advanced algorithms could improve urban traffic flow.
No commits in the last 6 months.
Use this if you need to evaluate and compare intelligent traffic light systems against traditional fixed-cycle approaches for a two-way single intersection.
Not ideal if you are looking to manage complex multi-intersection networks or require a system ready for immediate deployment in a live environment.
Stars
13
Forks
1
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rChimisso/2WSI-RL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FYP-ITMS/Intelligent-Traffic-Management-System-using-Machine-Learning
We developed a system that leverages on YOLO Machine Learning Model for managing the traffic...
Bellspringsteen/OurCamera
https://www.nytimes.com/2018/03/15/nyregion/bike-lane-blocked-new-york.html
Arup3201/SmartFlow-Traffic-Manager
An intelligent traffic management system to guide traffic authorities understand the trends of...
yossidoctor/AI-Traffic-Lights-Controller
Using reinforcement learning and genetic algorithms to improve traffic flow and reduce vehicle...
saraivacode/AIMS
Framework for classifying how network slicing policies impact Intelligent Transportation Systems...