GridWorld - 2D Reinforcement Learning Simulation

GridWorld is a 2D simulation game designed to help users experiment with reinforcement learning algorithms such as Value Iteration, Q-Learning, and Monte-Carlo. The game provides an engaging environment to learn and apply reinforcement learning concepts.

Features

• Train agents to complete predefined tasks.
• Analyze agent performance and decision-making.
• Compare different reinforcement learning algorithms.
• Interactive and educational platform for reinforcement learning.

Getting Started

Prerequisites

Ensure you have the following installed before running the project:

• Node.js (v16+ recommended)
• npm or yarn package manager

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/gridworld.git

2. Navigate to the project directory:

   cd gridworld

3. Install dependencies:

   npm install

   or if you're using yarn:

   yarn install

Running the Application

To start the application in development mode, run:

npm run dev

For production build, use:

npm run build
npm start

Usage

• Launch the application and select an agent to train.
• Choose an algorithm (Value Iteration, Q-Learning, Monte-Carlo).
• Observe the learning process and analyze agent decisions via visualizations.

Technologies Used

• React – for building the user interface.

Contributing

Contributions are welcome! To contribute:

1. Fork the repository.
2. Create a feature branch (feature/new-feature).
3. Commit your changes with clear messages.
4. Push to your fork and submit a pull request.