Decentralized Deep Reinforcement Learning based Real-World Applicable Traffic Signal Optimization

dITC through RL Code Foundation

An open-source Python implementation and evaluation of the Priority Bidding Mechanism (PBM) for adaptive traffic signal control. This is an active collaboration between the Illinois Mathematics and Science Academy and Southern Illinois University, Carbondale.

Оптимизация дорожного трафика на графе городских улиц с использованием квантово‑вдохновлённых методов

SynapticGrid is an AI-driven system designed to make cities more efficient, sustainable, and livable by optimizing smart energy grids, waste management, and traffic flow through IoT sensors, real-time data processing, and reinforcement learning algorithms. The modular platform continuously learns and improves, helping urban environments

SUMO

A novel integration of Large Language Models, Graph Neural Networks, and Reinforcement Learning for intelligent network traffic prediction and adaptive routing optimization. Demonstrates 42.3% throughput improvement and effective multi-objective optimization.

A Traffic Optimization system in C++ using a rudimentary ant colony optimization technique.

a prototype dashboard interface for the EV management via traffic and battery SoC, SoH optimisation

🚦 Next-generation AI Traffic Management System with real-time computer vision, reinforcement learning optimization, emergency vehicle detection, and immersive 3D visualization

This project aims to reduce traffic congestion at the Sadahalli toll gate using Queuing Theory and Linear Programming. By analyzing traffic flow and optimizing lane allocation, it successfully cuts down waiting time and improves toll booth efficiency.

DeepTrafficQ is a reinforcement learning-based traffic signal control system that uses Deep Q-Networks (DQN) to minimize vehicle waiting times at a 4-way intersection. By leveraging Q-learning with experience replay and a convolutional neural network (CNN), the agent dynamically adjusts traffic light phases to optimize traffic flow.

Analysis of modern network protocols designed to maintain data integrity and availability in adversarial environments.

An intelligent traffic optimization system using Deep Reinforcement Learning (DQN & Actor-Critic) to control vehicle speed and lane changes for improved traffic flow and safety.

This project uses reinforcement learning to optimize traffic signals, reducing congestion and improving flow through dynamic adjustments and simulation analysis.

Network Dynamics and Learning — Coursework and projects exploring network theory, optimization, and learning on graphs. Includes Jupyter notebooks with simulations, analysis, and visualizations using Python

Analysis of modern network protocols designed to maintain data integrity and availability in adversarial environments.