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 · Mini Project
Snake Game AI Bot
A deep Q-learning agent that teaches itself to play Snake
1-2 weeks build
Overview
A Pygame version of Snake paired with a deep Q-network agent that learns from scratch. The agent sees a compact state of nearby dangers, current direction and food position, earns rewards for eating and penalties for dying, and trains with experience replay. A live plot tracks score per game so you can watch the learning curve as it plays.
What makes it stand up
- 01Snake game in Pygame with a step-based training mode
- 02Eleven-value state encoding of danger, direction and food
- 03Deep Q-network with experience replay
- 04Epsilon-greedy exploration with decay
- 05Live score and moving-average training plots
Module breakdown
- 01
Game engine
Grid-based Snake with a controllable step function.
- 02
State and reward
Encodes the board and scores each move.
- 03
Q-network
Small PyTorch network predicting action values.
- 04
Training loop
Replay memory, target updates and checkpoints.
- 05
Monitoring
Plots scores and saves the best-performing model.
After this, you will be able to
- Explain the Bellman equation behind Q-learning
- Defend your reward design and its trade-offs
- Demo a trained agent next to an untrained one
Technology stack
- Python
- PyTorch
- Pygame
- NumPy
- Matplotlib
- Level
- Mini Project
- Domain
- Artificial Intelligence
- Build time
- 1-2 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