An interactive web application for visualizing and comparing different reinforcement learning algorithms in a grid world environment.

• Interactive grid world environment with:
  • Goal state (green)
  • Penalty state (red)
  • Agent (blue)
• Multiple RL algorithm implementations:
  • Q-Learning
  • DQN (Deep Q-Network)
  • REINFORCE (Policy Gradient)
• Real-time visualization of learning process
• Cumulative reward tracking
• Customizable hyperparameters
• Policy visualization and playback

1. Clone the repository:

git clone https://github.com/LukeKulm/Reinforcement-Learning-Visualization.git
cd rl-visualization

2. Create and activate a virtual environment:

On Windows:

python -m venv venv
venv\Scripts\activate

On macOS/Linux:

python -m venv venv
source venv/bin/activate

3. Install the required packages:

pip install -r requirements.txt

1. Make sure your virtual environment is activated
2. Start the Flask server:

python app.py

3. Open your web browser and navigate to:

http://localhost:5000

rl-visualization/
├── backend/
│   ├── agents/         # RL algorithm implementations
│   ├── environment/    # Grid world environment
│   └── utils/          # Helper functions
├── frontend/
│   ├── static/         # CSS, JavaScript, and assets
│   └── templates/      # HTML templates
└── api/                # Flask API endpoints

This project is licensed under the MIT License - see the LICENSE file for details.