PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Learn to Drive with Reinforcement Learning
Agents learn to lap a 2D Pygame track by trial and error
3-4 weeks build
Overview
A top-down Pygame track where a car senses the walls through ray-cast distances and must learn to drive without crashing. Two learners are built on the same environment: a population of small neural networks evolved with a genetic algorithm, and a DQN agent with experience replay, so the report can compare how each learns and where each gets stuck.
What makes it stand up
- 01Custom Gym-style environment with ray-cast sensors and rewards
- 02Neuroevolution with selection, crossover and mutation
- 03DQN with replay buffer and target network
- 04Track editor for drawing new circuits to test generalisation
- 05Learning curves and saved replays for every experiment
Module breakdown
- 01
Environment
Pygame physics, sensors, collisions and reward shaping.
- 02
Genetic algorithm
Population of networks evolved across generations.
- 03
DQN agent
Q-network, epsilon schedule and replay training loop.
- 04
Track editor
Draw, save and load circuits and checkpoints.
- 05
Analysis
Reward curves, lap times and side-by-side replays.
After this, you will be able to
- Explain reward shaping and how it changes behaviour
- Compare evolution and Q-learning on the same task
- Demo a trained car lapping a track it never saw
Technology stack
- Python
- PyTorch
- Pygame
- NumPy
- Matplotlib
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support