Yet another Hacker News

Show HN: A competition for small neural networks that play strategy games

39 points codetiger 11 hours ago 11 comments

codetiger 10 hours ago | parent

15yrs back I participated in "Google Ants AI Challenge 2011", an ai programming competition, hosted by the University of Waterloo, and I ranked #127 (#1 in my country). The competition gave me a huge learning oppurtunity where developers across the world came to a forum and discussed various techniques.

Now, I've built a similar platform to bring back the fun of building a small neural network that can play the game well. Neural Network optimization seems to be much more fun.

Plz share your feedback to improve the platform and add more games.

atmanactive 7 hours ago | parent

I remember a game on Steam called Tiny Brains, great couch co-op.

AnotherGoodName 44 minutes ago | parent

Nice. I was 72nd. Working in AI research today and still making ai for games as a hobby (tfmbot.com is an ai i’m working on for my favourite board game terraforming mars).

codetiger 21 minutes ago | parent

Thanks for sharing. I remember #1 xathis had a score, big leap ahead of others. The difference in techniques in top 100 was almost the same.

adityamishra241 8 hours ago | parent

This looks fun. How small are the networks you're aiming for?

sitzkrieg 2 hours ago | parent

the network size brackets are in TFA:

    nano up to 16 KiB
    micro up to 128 KiB 
    mini up to 1 MiB 
    small up to 8 MiB 
    large up to 64 MiB

lostdog 1 hour ago | parent

Cool idea!

It would help to delete all the text on the page, and write it without AI.

For example, "model and manifest bytes together pick the class; every version also plays on Open"

codetiger 17 minutes ago | parent

Thanks for the feedback. I’ll take that as top priority.

lokar 54 minutes ago | parent