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

[euroderf]

Let's play real stuff.

"Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks"

https://arxiv.org/pdf/2502.13918

[TeMPOraL → euroderf]

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.

[euroderf → TeMPOraL]

No no no it's not a game named Hex. It's a gaming genre where units move on a field of hexagons.