MIT's Ataraxo AI beats top Stratego players with self-play and decision-time planning
nordicinst · x · 2026-09-30
MIT News reports that Ataraxos, developed by researchers at MIT, CMU, NYU, and Stanford, defeats top-ranked human Stratego players while using fewer resources than other models. It combines self-play with decision-time planning to scale to imperfect-information games, an area where poker-style AI techniques break down due to an explosion of possible game states. Researchers see potential applications in military maneuvers and business negotiations.
More from Research
- Meta, Stanford and Harvard open up ProgramBench leaderboard with community submissions — jyangballin · 2026-09-30
- AI's "OH MY GOD!" exclamations may actually help its reasoning — danintheory · 2026-09-30
- Poison sample selection swings LLM backdoor attack success from 3% to 80% — chhaviyadav_ · 2026-09-30
- Rewriting the ELBO Explainer for Diffusion Language Model Training — zmkzmkz · 2026-09-30
- Google DeepMind scientist releases 58-page paper on game-theory-specialized agents — mdancho84 · 2026-09-30
- Tokens Are Just Integer IDs: The Comma Is Row 28 of the Embedding Matrix — zsakib_ · 2026-09-30