
What happened
The AI Ataraxos beat Niemeijer, the most decorated Stratego player, with an 85 percent effective win rate over three weeks, at a compute cost of less than $8,000.
Why it matters
This marks a breakthrough in imperfect-information games, showing that reinforcement learning can handle large amounts of hidden information where poker-derived methods previously struggled.
What to watch
The researchers say more compute time won't improve Ataraxos's performance unless a more sophisticated search method is developed; the code is publicly available for others to build on.
WHO IT HITSThis work signals that AI can now tackle complex strategic decision problems with hidden information using modest budgets, potentially benefiting researchers and businesses in fields like finance, military planning, and negotiations.
Summaries like this, every morning.
Stratego has long been a tough challenge for AI because both players set up their 40 pieces face down, creating more than 10^33 possible setups. In such games, the value of a move depends on hidden information, and poker AI methods only worked when little was hidden. DeepMind's DeepNash trained on 1,024 TPU nodes for two to three months, costing an estimated $3 million to $4.5 million at 2025 prices, yet failed to beat top humans. In contrast, Ataraxos needed one week on 16 Nvidia H100 GPUs and four more days on four GPUs, costing less than $8,000. The researchers credit a custom GPU simulator and higher sample efficiency.
The key to Ataraxos's success is regularization, which forces the AI to vary its play and avoid predictable strategies. It also uses a belief network to predict hidden pieces. The researchers tested Ataraxos against Niemeijer over three weeks, with Niemeijer receiving $1,000 plus bonuses for wins and draws. The AI won with an 85 percent effective win rate, a result described as unprecedented at the highest level. Niemeijer could adapt over many games, but the AI could not adapt to him, which three-time world champion Vincent de Boer called a major handicap. At the 2025 Stratego World Championship exhibition, Ataraxos won 38 of 40 games.
The method also worked in other games: Barrage Stratego, Hanabi, and Dou dizhu. The authors argue that large amounts of hidden information are no longer an obstacle for reinforcement learning, opening up practical AI for strategic decision problems like financial markets, military conflicts, and negotiations—provided fast simulators can be built. One limitation: the search only mimics a single learning step, so adding compute won't keep improving performance without a more sophisticated search method. The code is publicly available, so others can test and extend the approach, but the real-world impact will hinge on whether suitable simulators exist for those domains.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
IMPACTLAKE began offering a ChatGPT plugin for impactlake(TM) and added Model Context Protocol (MCP) support…

The author installed the open-source agent platform OpenClaw on an EPSON Endeavor NY2100S (Celeron P4600, 4GB…

A developer using Claude Code on a personal web app discovered via --debug logs that his Stop hook passed ever…

Internal documents seen by Reuters show Amazon plans a "World Product Graph" catalog of global product data, i…

株式会社粋農 implemented MCP (Model Context Protocol, a common standard linking AI apps to external data and functio…

AIworker published a free November 2026 report on structuring Microsoft 365 Copilot training for company-wide…
