--- id: "2026-09-30-ataraxos-stratego-nature" url: "https://postcutoff.com/e/2026-09-30-ataraxos-stratego-nature/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-09-30" date_precision: day category: research importance: 3 confidence: high status: [Confirmed] sources: 4 editor: human editor human_review: null version: "2026-10-04" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-30-ataraxos-stratego-nature/ # Ataraxos beats Stratego's top player 15-1-4 at a fraction of DeepNash's compute Full title: Ataraxos beats Stratego's top player 15-1-4 at a fraction of DeepNash's compute (Nature) On Sept 30, 2026 Nature published Ataraxos, a Stratego AI from researchers at MIT, CMU, NYU and Stanford led by MIT's Gabriele Farina. It beat Pim Niemeijer, the game's most decorated player, 15 wins, 1 loss and 4 draws, and went about 38–39 wins to 2 losses against elite players at a world championship exhibition. It combines self-play RL with decision-time planning over a learned belief model of hidden pieces. It beat DeepMind's DeepNash using under 1% of its training examples and a few thousand dollars of GPU time. ## Key facts - Paper: 'Scalable decision-making for games of imperfect information', Nature, Sept 30, 2026 (preprint on arXiv Nov 2025) - Lead: Gabriele Farina (MIT EECS); collaborators at Carnegie Mellon, NYU and Stanford - Vs Pim Niemeijer: 15 wins, 1 loss, 4 draws over 20 games - World-championship exhibition vs elite players: reported as 38-2 (MIT News via SiliconSnark) or 39-2 (other reports) - Reaches 'strictly higher playing strength than DeepNash while using less than one hundredth of the training examples'; the paper estimates DeepNash would cost $3–4.5M to train today - Training: 16 NVIDIA H100s for about a week, plus 4 H100s for 4 days for the belief network (reported) - Also superhuman Barrage Stratego, and state-of-the-art Hanabi and dou dizhu results ## What happened Stratego hides each piece's identity, which makes classic game-tree search hard. DeepMind's DeepNash (2022) reached expert level with huge compute and no search. Ataraxos instead plans at decision time over sampled hidden states from a generative belief network, and needs far less training. ## Why it matters It shows how cheap superhuman play in a large imperfect-information game has become. Explicit belief modelling plus search beats brute-force self-play, a lesson relevant to agents that act under hidden information. Unverified: the exhibition record differs between reports (38-2 vs 39-2); the Nature paper itself was paywalled in this run. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 122 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 92 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 183 days after its cutoff - Grok 4.7 (training cutoff May 2026): 122 days after its cutoff ## Sources 1. [Nature: Scalable decision-making for games of imperfect information](https://www.nature.com/articles/s41586-026-11036-y) (nature.com, paper) 2. [Ars Technica: AI finally beat the best Stratego player in history, and did it on a budget](https://arstechnica.com/science/2026/10/ai-finally-beat-the-best-stratego-player-in-history-and-did-it-on-a-budget/) (arstechnica.com, press) 3. [SiliconSnark: MIT's Ataraxos beats Stratego champions](https://www.siliconsnark.com/mits-ataraxos-beats-stratego-champions-without-requisitioning-a-small-power-plant/) (siliconsnark.com, press) 4. [AI Weekly: Ataraxos AI tops Stratego champion for a few thousand dollars](https://aiweekly.co/alerts/ataraxos-ai-tops-stratego-champion-for-a-few-thousand-dollars) (aiweekly.co, press) ## Changes - 2026-10-04: Added Ars Technica coverage (HN front page, 277 pts) - 2026-10-01 (filed): Created