‹ BackHN Continuity

Thread

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

116 points · 41 comments · codetiger

  1. codetiger · · focus · HN ↗
    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.

    1. atmanactive · · focus · HN ↗
      I remember a game on Steam called Tiny Brains, great couch co-op.
    2. AnotherGoodName · · focus · HN ↗
      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).
      1. codetiger · · focus · HN ↗
        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.
    3. Muthaalagan · · focus · HN ↗
      From competing with the world to building a place for the world to compete—what a full-circle moment. Love the challenge: how much strategy can a tiny neural network learn? Excited to see what people build.
    4. nickledave · · focus · HN ↗
      Nice work, the new site looks great.

      Can you give more background on the Ants game?

      I didn't find it on the current site or the older one.

      Was the game inspired by anything like agent-based simulations?

      I&#x27;m not super interested in what the tech industry is calling &quot;agentic&quot; AI, but I am interested in collective intelligence, see David Ha&#x27;s work in this area: - <a href="https:&#x2F;&#x2F;journals.sagepub.com&#x2F;doi&#x2F;full&#x2F;10.1177&#x2F;26339137221114874" rel="nofollow">https:&#x2F;&#x2F;journals.sagepub.com&#x2F;doi&#x2F;full&#x2F;10.1177&#x2F;26339137221114... - <a href="https:&#x2F;&#x2F;neurips.cc&#x2F;virtual&#x2F;2024&#x2F;105817" rel="nofollow">https:&#x2F;&#x2F;neurips.cc&#x2F;virtual&#x2F;2024&#x2F;105817

      Would be cool if each ant itself could be an agent

      1. codetiger · · focus · HN ↗
        Unfortunately the competition site is mostly down and couldn&#x27;t find much about the old competition other than the participants blog articles. Do a search on &quot;Google Ants AI Challenge - post mortem&quot;, and you get a lot of articles around the game.

        Thanks for sharing the research. I tried implementing a per Ant decision making model, but gave up as the training time was much longer compared to the current baseline. I think I should rethink the idea.

        1. nickledave · · focus · HN ↗
          Understood, thanks! We must need smaller models :)
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.