MarI/O - Machine Learning for Video Games

SethBling · 10 recommenders · 10 months

SethBling shows MarI/O, a program using neural networks and the NEAT genetic algorithm to learn to play Super Mario World. The description links the source code, the paper and background reading.

Why Hacker News readers recommend it: The go-to accessible introduction to neuroevolution and NEAT, praised for crediting prior research.

10 recommenders3 strong recommendations2015–2026

Machine learning & deep learning Speedrunning, glitches & game hacking#neat#genetic algorithms#neural networks#super mario world#machine learning

“his brief videos give a really nice introduction to the topic that should be accessible to most people”
View the original HN discussion

Related videos

The spelled-out intro to neural networks and backpropagation: building micrograd

But what is a neural network? | Deep learning chapter 1

SM64 - Watch for Rolling Rocks - 0.5x A Presses (Commentated) [OUTDATED]

Reverse emulating the NES to give it SUPER POWERS!

AlphaGo - The Movie | Full award-winning documentary

Transformers, the tech behind LLMs | Deep Learning Chapter 5

USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?

Lecture 1 | Machine Learning (Stanford)