How nithin0702/smart-bus-route-optimization-using-deep-reinforcement-learning works
This repository presents a smart-bus routing simulation using reinforcement learning. In Q_Learning.py, the simulation creates a route network, bus and passengers; the bus selects routes, passenger pickups and elapsed time produce rewards for Q-table updates, and the loop renders the result. Environment.py is a separate Pygame route visualizer. The README also describes Deep Q-Learning, and DQN_Final_Train_Test.py is named accordingly, but its implementation and connections were not sampled. The diagram therefore shows that capability without guessing its runtime wiring.
Main entry points: Q_Learning.py Bus Agent
Components 7
Bus Simulation
- Route Network
Q_Learning.py - Bus Agent
Q_Learning.py - Passengers
Q_Learning.py - Simulation Loop
Q_Learning.py
Learning Approaches
- Q-Learning
Q_Learning.py - DQN Training/Test
DQN_Final_Train_Test.py
Route Visualization
- Environment Viewer
Environment.py
Connections 6
- Simulation Loop → Bus Agent: updates
Q_Learning.py - Simulation Loop → Passengers: updates
Q_Learning.py - Simulation Loop → Bus Agent: rewards
Q_Learning.py - Bus Agent → Route Network: follows
Q_Learning.py - Bus Agent → Passengers: checks pickups
Q_Learning.py - Bus Agent → Q-Learning: updates values
Q_Learning.py