Skip to content

An alternate way to view the Minigrid environment using animations and sprites. Intended to be used as a teaching tool for kids to promote more engagement and interest in Reinforcement Learning.

License

Notifications You must be signed in to change notification settings

NSChristopher/Minigrid_with_Sprites

 
 

Repository files navigation

MiniGrid with Sprites

License Version Status

Door Key Unlock
Unlock Unlock

An alternate way to view the Minigrid environment using animations and sprites. Intended to be used as a teaching tool for kids to promote more engagment and interest in Renforcemnt Learning.

Table of Contents

About the Project

Designed to engage students in learning about AI and reinforcement learning specifically, Minigrid with Sprites adds an entirely new rendering manager to Minigrid. This rendering manager utilizes Pyglet along with tons of custom logic to create a beautifully rendered environment for any Minigrid environment.

Features

  • Sprites and Animations: Using pyglet Minigrid environmnets can be rendered with any sprite.
  • Seperate Rendering Logic: The rendering logic is now seperated and much easier to customize.

Getting Started

# Clone the repository
git clone https://github.com/NSChristopher/Minigrid_with_Sprites.git

# Navigate into the project directory
cd repository

# Install dependencies
pip install -r requirements.txt

Usage

Import the PrettyRenderingManager along with the gym and your desired environment.

import gymnasium as gym
from minigrid.envs import LavaGapEnv
from minigrid.rendering.pretty_rendering_manager import PrettyRenderingManager

Pass the new PrettyRenderingManager into the env.

env = LavaGapEnv(render_mode='rgb_array', rendering_manager=PrettyRenderingManager,size=6)

Contact

Noah Christopher - noah.dev@outlook.com

Project Link: Minigrid_with_Sprites

Acknowledgements

About

An alternate way to view the Minigrid environment using animations and sprites. Intended to be used as a teaching tool for kids to promote more engagement and interest in Reinforcement Learning.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 85.6%
  • Jupyter Notebook 14.2%
  • Other 0.2%