TinyBrains - Competition for tiny neural networks that play strategy games
Show HN: A competition for small neural networks that play strategy games
TinyBrains challenges you to build the smallest neural network that plays well. Based on the classic Ants game from Google AI Challenge 2011, you train a network, describe it in a manifest, and submit both. Models are measured into weight classes based on total bytes—from 16 KiB nano to 64 MiB large. The goal isn't the strongest player, but the strongest play packed into the fewest bytes. Compete on the leaderboard, watch matches, and see how your tiny brain stacks up.
The contest is not who can build the strongest player, but who can pack the strongest play into the fewest bytes.
- codetiger
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.
- euroderf
Let's play real stuff.
"Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks"
- adityamishra241
I remember the Google Ants challenge being pretty interesting. What made you choose strategy games for the new competition instead of something simpler like classic board games?
- b800h
Around 1997 there was something awfully similar to this doing the rounds, called AI Wars. IIRC it was code rather than weights, but it's a funny parallel. 30 years! God I'm old.
- WanderZil
This reminds me of John Conway's Game of Life. I wonder what surprises we could get by combining Game of Life with neural networks