← Saturday, October 3, 2026Models & trainingNews

Ataraxos beats elite Stratego players using 16 GPUs and a few thousand dollars

arstechnica.com 6 min read Editor score 7/10

Ataraxos beat Pim Niemeijer 15 games to one, with four draws, after training on 16 GPUs for a few thousand dollars. The result is a concrete example of applied AI tackling imperfect-information play at modest stated compute cost.

What: Ataraxos is an AI that beat Stratego player Pim Niemeijer 15–1, with four draws.
How: It trained on 163 million self-play games; a belief model inferred hidden pieces to support search before each move.
Why it matters: Combining learned beliefs with lookahead brings search to a long, hidden-information game that earlier systems struggled to solve.

Ataraxos uses self-play for training and a belief model to inform search before a move. Sketched from the article's own text.

Read on arstechnica.com → Hacker News · 98 comments

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.