Adaptive Traffic DQN

Overview

A reinforcement-learning simulation for traffic lights that learns signal actions from changing road conditions. Using a Deep Q-Network, the controller adapts its choices as traffic shifts, with the goal of reducing waiting and congestion. The project offers a compact testbed for exploring how learned traffic control behaves across different simulated scenarios.

Source code

Black and white diagram for Adaptive Traffic DQN: a learned traffic signal chooses actions from the changing flow at a road intersection