Skip to content

README.md

Latest commit

 

History

History
59 lines (42 loc) · 2.5 KB

README.md

File metadata and controls

59 lines (42 loc) · 2.5 KB

AI-Racing-Sim

Welcome to the Car Racing AI Game project! This project is built using Python, Pygame, and Gymnasium. It features a car racing game with AI-controlled cars navigating through randomly generated race tracks. The AI cars are currently under development and will be capable of driving autonomously once trained.

Features

  • AI Cars: The game is focused on developing AI cars that can navigate race tracks autonomously using reinforcement learning.
  • Random Track Generation: Each game session generates a new, random race track, ensuring a unique experience every time.
  • Smooth Gameplay: Built using Pygame, the game offers realistic car behavior and visual feedback.
  • Customizable: The project is open-source and easy to customize, making it suitable for further development and experimentation.

SneekPeek

Sim-Racer_Decan.mp4

Git_Post0 Info Git_Post1

Controls

  • T: Toggle between AI drive and manual drive
  • F: Display information tab
  • SPACE: Change to a new random track
  • R: Reset on the current track

Prerequisites

Before running the project, make sure you have the following libraries installed:

  • Python 3.8+
  • Pygame
  • Gymnasium
  • NumPy
  • PyTorch
  • StableBaselines3

Comand to install all Prerequisites :

pip install pygame gymnasium numpy torch stable-baselines3

Use Cases

  1. AI Development and Testing:

    • Experiment with AI training scripts to develop autonomous driving behavior.
    • Observe how the AI models adapt to randomly generated tracks, providing insight into their learning process.

  2. Game Development Learning:

    • Explore how Pygame and Gymnasium are used together to build dynamic game environments.
    • Understand the integration of reinforcement learning models into game mechanics.

  3. Random Track Generation:

    • Developers can enhance and modify the track generation algorithms to create more varied and complex racing environments.
    • Track customization can be used to test different AI driving behaviors and strategies.

  4. Reinforcement Learning Experimentation:

    • Use the project as a sandbox to apply different reinforcement learning techniques.
    • Experiment with training parameters, reward systems, and learning algorithms to improve the AI’s racing skills.