5 comments

[ 2.7 ms ] story [ 22.5 ms ] thread
I was expecting something like DQN, but what I actually saw was a new approach, so it was fascinating. Usually when you're making small AI demos and doing hands-on exercises, you work with Tetris a lot.

In NES Tetris, if the input is the same, the result is the same, so you can store all the inputs and reproduce specific moments. The state becomes like a graph, which allows for fuzzing testing. It's interesting

I'm the author. Thanks for the comments.
Great post! Thanks for the write up, enjoyed reading it and the visuals.