This game-playing AI is the new champ at Stratego

PUBLISHER ARTICLE PREVIEW

From the original article

Images for download on the MIT News office website are made available to non-commercial entities, press and the general public under a Creative Commons Attribution Non-Commercial No Derivatives license. You may not alter the images provided, other than to crop them to size. A credit line must be used when reproducing images; if one is not provided below, credit the images to "MIT."

A new AI system that excels at challenging games with hidden information could someday help human decision-makers select ideal strategies to outfox opponents in complicated situations like military maneuvers.

Using advances in machine-learning, researchers from MIT, Carnegie Mellon University, New York University, and Stanford University developed an AI that defeated top-ranked human players of the board wargame Stratego by a large margin — something no AI system had been able to achieve.

Stratego, a two-player game of imperfect information, in which the opponent’s piece identities remain hidden, is often used as a benchmark to test the strategic thinking abilities of powerful AI models.

To build their model, the researchers combined efficient training algorithms with new techniques tailored for calculated decision-making in hidden information settings.

The AI system achieved greater performance at Stratego than the next best models, while being far cheaper and less computationally demanding to train. The system also outperformed top human players in other strategic games with different rules and designs, demonstrating how it can be generalized for a variety of use-cases.

The AI system could be adapted to help humans tackle many real-world problems with hidden information, such as business negotiations or cybersecurity.

“In the kind of imperfect information tasks you would face in reality, you often don’t have the luxury of enumerating through all the possibilities. There are just too many. Having AI algorithms that are general purpose and can provably perform this challenging task so well is a big step forward,” says Gabriele Farina, an assistant professor in the Department of Electrical Engineering and Computer Science (EECS), principal investigator at the Laboratory for Information and Decision Systems (LIDS), and senior author of a paper on this AI system.

He is joined on the paper by lead author Samuel Sokota, a graduate student at Carnegie