Stratego stumped AI for years — a new Nature paper finally cracks it
PaulHoule · hn · 2026-10-02
Hacker News is discussing a new Nature paper (preprint on arXiv) showing AI has finally cracked Stratego, the classic board game that long stumped machines.
Unlike Go or chess, Stratego is a hidden-information game with concealed piece identities and an enormous information space, so standard search and reinforcement-learning approaches don't transfer directly. The new method reaches unprecedented play strength in this imperfect-information setting, marking a notable milestone for AI decision-making under hidden information. Links to the paper and arXiv version are in the post.
More from Research
- Paper resolving a 15-year-old AdaBoost question, aided by LLMs, accepted to NeurIPS 2026 — chetanp · 2026-11-19
- Anthropic analyzes 207k research sessions: data analysis dominates, formal sciences use Claude most — plopesresearch · 2026-11-19
- Ramp releases SWE-Bench v2: 500 production-built tasks, 6.2 Astra tops at 76.4% — AniBaddepudi · 2026-11-19
- Stanford's Le Cong to talk AI co-scientists for RNA design at 14th mRNA Health Conference — MengdiWang10 · 2026-11-19
- New paper shows DiT latents can be linearly probed to predict pixels, skipping the VAE decoder — kwangmoo_yi · 2026-11-19
- SAIL 2027 opens abstract submissions for AI in clinical care, deadline Jan 15 — zakkohane · 2026-11-19