Thread

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

116 points · 41 comments · codetiger

euroderf · 1789998000 · focus · HN ↗
Let's play real stuff.
"Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks"
<a href="https://arxiv.org/pdf/2502.13918" rel="nofollow">https://arxiv.org/pdf/2502.13918
1. TeMPOraL · 1790012867 · focus · HN ↗
  Is "Hex" real stuff? I know that from university AI courses, from before current ML phase. I thought this was a toy game invented specifically to be nice for AI exercises - bounded, easy to follow, moderate branching factor, and designed to make ties impossible.
  1. euroderf · 1790020635 · focus · HN ↗
    No no no it's not a game named Hex. It's a gaming genre where units move on a field of hexagons.

Unofficial Hacker News client; not affiliated with Y Combinator.