Paperspace/DinoRunTutorial

Accompanying code for Paperspace tutorial "Build an AI to play Dino Run"

50
/ 100
Established

This project helps anyone interested in seeing how artificial intelligence can learn to play a simple game without being explicitly programmed. It takes the visual input of the Dino Run game and produces game actions (jump or duck). This is for educators, hobbyists, or students curious about reinforcement learning and game AI.

326 stars. No commits in the last 6 months.

Use this if you want to understand how a computer can learn to play a game just by looking at the screen, using a reinforcement learning approach.

Not ideal if you're looking for a general-purpose gaming AI framework or a deep-dive into complex game theory strategies.

game-ai reinforcement-learning-tutorial educational-ai computer-vision-for-games
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

326

Forks

101

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 15, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Paperspace/DinoRunTutorial"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.