Fershad Irani

Digital Sustainability Consultant
This website is grid-aware, some functionality has changed based on your local energy grid. Find out more.
Note

Learning about training AI and learning about ourselves

Published:

Table of Contents

Peter Whidden's put together a project to train an AI how to play Pokemon Red using reinforcement learning. That's cool by itself, especially when you see the whole thing come together in the awesome YouTube video he's created (linked below).

What's even more compelling is Peter's explanation of the process. It's not just a clear, easy to follow explanation of how an AI model can be trained with reinforcement learning, it even includes some food for thought about just how similar the AI decision process is to our own.

Definitely give yourself 20-30 minutes to check out Training AI to Play Pokemon with Reinforcement Learning on YouTube.