GoKawiilDeveloper runs tiny AI world model and game-playing agent on Raspberry Pi Pico 2 W
A hobbyist built two small neural networks—a looped transformer 'world model' that generates game frames and rewards, and a lightweight MLP 'actor' that chooses actions—running together entirely on a Raspberry Pi Pico 2 W microcontroller. The world model, ranging from 26,000 to 131,000 parameters, predicts the next frame and reward from the current frame and action, while the actor (9,000-16,000 parameters) picks moves based only on generated frames, never touching the real game logic. The project also supports a streaming reinforcement learning agent that can learn to play while running inside the simulated 'dream' itself.