A full-stack intelligent tutoring system that uses Reinforcement Learning (Q-Learning) to personalize educational content delivery based on individual student performance and learning patterns.

This university mini-project demonstrates a practical application of reinforcement learning in education. The system adapts to each student's knowledge level and learning style, recommending appropriate content in real-time using a Q-Learning agent.

• 🧠 Q-Learning Agent - Adaptive content recommendation
• 📊 Real-time Analytics - Track progress and performance
• 🎨 Modern UI - Beautiful landing page with Aceternity UI
• 🔐 Secure Authentication - JWT-based with refresh tokens
• 📈 Progress Tracking - Detailed learning analytics
• ⚡ Fast Backend - FastAPI with async support
• 🎮 Interactive Demo - Try the system without signup
• 🔍 RL Visualization - See how Q-Learning works
• 🧪 Comprehensive Tests - 90%+ test coverage

• Node.js 18+
• Python 3.8+
• npm or yarn

# Install dependencies
npm install

# Run development server
npm run dev

Visit: http://localhost:3000

# Navigate to backend
cd backend

# Create virtual environment
python -m venv venv

# Activate virtual environment (Windows)
venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Seed database
python seed_db.py

# Run server
  
  python -m uvicorn main:app --host 0.0.0.0 --port 8002

Visit: http://localhost:8000/docs (API Documentation)

mini_project/
├── app/                      # Next.js Frontend
│   ├── components/ui/       # Aceternity UI components
│   ├── lib/                 # Utilities
│   └── page.tsx            # Landing page
├── backend/                 # FastAPI Backend
│   ├── app/
│   │   ├── api/            # API endpoints
│   │   ├── core/           # Configuration
│   │   ├── models/         # Database models
│   │   └── services/       # RL Agent & Student Model
│   ├── main.py             # FastAPI app
│   └── seed_db.py          # Database seeding
├── INTEGRATION.md          # Integration guide
├── PROJECT_SUMMARY.md      # Detailed project info
└── TODO.txt               # Project checklist

• POST /api/v1/auth/register - Register new student
• POST /api/v1/auth/login - Login and get JWT token

• POST /api/v1/session/start - Start session, get recommended content
• POST /api/v1/session/answer - Submit answer, get feedback
• GET /api/v1/session/progress - Get learning progress

• GET /api/v1/analytics/dashboard - Complete dashboard data
• GET /api/v1/analytics/rl-stats - RL agent statistics

• State Space: 4D knowledge vector (algebra, calculus, geometry, statistics)
• Action Space: Content selection from available pool
• Reward Function:
  • Correctness (+1.0 correct, -0.5 wrong)
  • Time efficiency (bonus for quick answers)
  • Difficulty appropriateness (bonus for matching level)
• Exploration: Epsilon-greedy (ε = 0.1)
• Learning Rate: α = 0.1
• Discount Factor: γ = 0.95

The project includes comprehensive test coverage:

cd backend
pytest test_rl_agent.py -v

cd backend
python test_integration.py

cd backend
python test_e2e.py

• Username: testuser
• Password: test123

Visit http://localhost:8000/docs for Swagger UI

See TESTING.md for complete testing guide

• Algebra: 5 questions (difficulty 1-4)
• Calculus: 4 questions (difficulty 1-4)
• Geometry: 4 questions (difficulty 1-3)
• Statistics: 4 questions (difficulty 1-3)

• Students, Content, LearningSession, StudentKnowledge, PerformanceMetrics

• INTEGRATION.md - Frontend-Backend integration guide
• PROJECT_SUMMARY.md - Complete project details
• backend/README.md - Backend documentation
• TODO.txt - Project progress checklist

• Next.js 16 + React 19
• TypeScript
• Tailwind CSS v4
• Framer Motion (as 'motion')
• Aceternity UI Components
• Lucide Icons

• FastAPI
• SQLAlchemy
• Pydantic
• JWT Authentication
• NumPy, Pandas, Scikit-learn

• SQLite (development)
• PostgreSQL (production ready)

✅ COMPLETED

• Backend API fully functional
• RL Agent implemented
• Database seeded with content
• Landing page with animations
• Authentication system
• Learning session management
• Analytics endpoints

⏳ IN PROGRESS

• Frontend-backend integration
• Dashboard UI
• Learning session interface

• Frontend: http://localhost:3000
• Backend API: http://localhost:8000
• API Docs: http://localhost:8000/docs
• Redoc: http://localhost:8000/redoc

• Sanskar Khandelwal - AI Research Lead
• Ayush Saroj - Full stack
• Krishna mittal- devops

1. Create API client in Next.js
2. Build login/register pages
3. Create student dashboard
4. Build quiz interface
5. Add progress visualization
6. Deploy to production

• Next.js Documentation
• FastAPI Documentation
• Q-Learning Tutorial

University Mini-Project | Reinforcement Learning Application | Educational Technology

• QUICKSTART.md - 5-minute setup guide
• DEPLOYMENT.md - Production deployment instructions
• TESTING.md - Complete testing guide
• COMPLETION_SUMMARY.md - Project overview
• PHASE_9_10_COMPLETE.md - Demo & testing features

Visit /demo to try a 5-step walkthrough of the system without creating an account.

Visit /rl-viz to see how the Q-Learning agent makes decisions in real-time.

Project Status: 98% Complete ✅
Last Updated: October 22, 2025

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.

This project is prepared to use components from Aceternity UI (Tailwind-based components).

Installed/required packages:

• Tailwind CSS v4 (already configured via @tailwindcss/postcss and @import "tailwindcss" in app/globals.css)
• motion (Framer Motion v11)
• clsx
• tailwind-merge
• lucide-react (icons)

Utility:

• lib/utils.ts exports a cn helper for merging class names with Tailwind-merge.

Optional install (if any of the above are missing):

npm i motion clsx tailwind-merge lucide-react

Usage example:

import { cn } from "@/lib/utils";

export function Example({ active }: { active?: boolean }) {
	return (
		<button className={cn("px-4 py-2 rounded-md", active && "bg-black text-white")}>Click</button>
	);
}