Learning Pokemon With Reinforcement Learning
A write-up of a reinforcement learning agent that learns to beat Pokemon Red with under ten million parameters, explaining the training approach and results.
No account needed · sign in to keep your taste everywhere
More like this
Pages that share this page's themes. Or browse all of Tech.
TinyPPO Snake
A neural network learns to play Snake live in your browser using PPO reinforcement learning, so you can watch it go from…
Blue Moon Falls
A loving fan guide to Pokemon generations 1 and 2, covering everything about Gold, Silver, Crystal, Red, Blue, and Yello…
Jay Alammar's Illustrated Guides
Illustrated guides that break down how transformers, GPT, and other AI models work using detailed step-by-step diagrams…
AI Weirdness
A machine-learning humor blog by Janelle Shane that trains neural networks on odd tasks and shares the results, from str…
Aman.ai
Stanford class notes and learning primers on artificial intelligence and deep learning, written as a clear reference for…
This Person Does Not Exist
Generates a new photorealistic face of a person who does not exist on each refresh, using a generative adversarial netwo…
Stumble onto more like this
One click takes you to a page you didn't know you were looking for. Rate it and the next one lands closer to your taste.
Add to Browser — it's freeWorks in Chrome, Edge and Brave. No account needed.