With most information hidden, the game Stratego had stumped AI until now
What happened
A team from Carnegie Mellon, MIT, NYU and Stanford trained an AI called Ataraxos that beat the top human Stratego player, Pim Niemeijer, 15‑to‑1 with four draws. The system uses two neural networks: one for general play and a second belief model that guesses the opponent’s hidden pieces, allowing it to sample plausible board states instead of enumerating all possibilities. Ataraxos was trained on 163 million self‑play games using only 16 GPUs and a few thousand dollars. The key innovation was making large strategic changes early in training and small ones later, and incorporating a forward‑looking search before each move.
Why it matters
The win shows that even games with massive hidden information can be mastered by relatively inexpensive AI, hinting at future applications in fields that rely on inference under uncertainty. It also suggests that advanced game‑playing techniques can be developed without the huge budgets once thought necessary.
Reality check
An automated, sceptical read of the sourceGenuine breakthrough. The article claims the first AI to reliably beat the best human Stratego player using modest resources and a novel belief‑model approach.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
AI unlocks Gödel's notebooks, said to contain hundreds of proved theoremsIndustry news · 13 Nov 2026Gemini 4 Hydrogen and OrchestratorIndustry news · 12 Nov 2026Gemini 4 HydrogenIndustry news · 12 Nov 2026I'm making LLMs work on small and old devicesIndustry news · 12 Nov 2026United Airlines bans AI agents from booking flights on behalf of travelersIndustry news · 11 Nov 2026This page was collected from arstechnica.com and summarised automatically by AIPulsee's pipeline. See how it runs.