logoalt Hacker News

jdw64today at 11:01 AM1 replyview on HN

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


Replies

jaffa2today at 11:31 AM

how doe piece selection work? isnt it random?

show 5 replies