Video games individuals — and machines — play: Untangling strategic reasoning to advance AI | MIT Information

Gabriele Farina grew up in a small city in a hilly winemaking area of northern Italy. Neither of his dad and mom had faculty levels, and though each have been satisfied they “didn’t understand math,” Farina says, they purchased him the technical books he needed and didn’t discourage him from attending the science-oriented, moderately than the classical, highschool.

By round age 14, Farina had targeted on an concept that may show foundational to his profession.

“I was fascinated very early by the idea that a machine could make predictions or decisions so much better than humans,” he says. “The fact that human-made mathematics and algorithms could create systems that, in some sense, outperform their creators, all while building on simple building blocks, has always been a major source of awe for me.”

At age 16, Farina wrote code to resolve a board recreation he performed together with his 13-year-old sister.

“I used game after game to compute the optimal move and prove to my sister that she had already lost long before either of us could see it ourselves,” Farina says, including that his sister was much less enthralled together with his new system.

Now an assistant professor in MIT’s Department of Electrical Engineering and Computer Science (EECS) and a principal investigator on the Laboratory for Information and Decision Systems (LIDS), Farina combines ideas from recreation concept with such instruments as machine studying, optimization, and statistics to advance theoretical and algorithmic foundations for decision-making.

Enrolling at Politecnico di Milano for school, Farina studied automation and management engineering. Over time, nonetheless, he realized that what activated his curiosity was not “just applying known techniques, but understanding and extending their foundations,” he says. “I gradually shifted more and more toward theory, while still caring deeply about demonstrating concrete applications of that theory.”

Farina’s advisor at Politecnico di Milano, Nicola Gatti, professor and researcher in pc science and engineering, launched Farina to analysis questions in computational recreation concept and inspired him to use for a PhD. At the time, being the primary in his speedy household to earn a school diploma and residing in Italy, the place doctoral levels are dealt with in another way, Farina says he didn’t even know what a PhD was.

Nevertheless, one month after graduating together with his undergraduate diploma, Farina started a doctoral diploma in pc science at Carnegie Mellon University. There, he gained distinctions for his analysis and dissertation, in addition to a Facebook Fellowship in Economics and Computation.

As he was ending his doctorate, Farina labored for a yr as a analysis scientist in Meta’s Fundamental AI Research Labs. One of his main tasks was serving to to develop Cicero, an AI that was in a position to beat human gamers in a recreation that entails forming alliances, negotiating, and detecting when different gamers are bluffing.

Farina says, “when we built Cicero, we designed it so that it would not agree to form an alliance if it was not in its interest, and it likewise understood whether a player was likely lying, because for them to do as they proposed would be against their own incentives.”

A 2022 article within the MIT Technology Review stated Cicero might symbolize development towards AIs that may remedy advanced issues requiring compromise.

After his yr at Meta, Farina joined the MIT school. In 2025, he was distinguished with the National Science Foundation CAREER Award. His work — primarily based on recreation concept and its mathematical language describing what occurs when totally different events have totally different goals, after which quantifying the “equilibrium” the place nobody has a motive to alter their technique — goals to simplify large, advanced real-world situations the place calculating such an equilibrium might take a billion years.

“I research how we can use optimization and algorithms to actually find these stable points efficiently,” he says. “Our work tries to shed new light on the mathematical underpinnings of the theory, better control and predict these complex dynamical systems, and uses these ideas to compute good solutions to large multi-agent interactions.”

Farina is particularly all in favour of settings with “imperfect information,” which implies that some brokers have info that’s unknown to different individuals. In such situations, info has worth, and individuals should be strategic about appearing on the knowledge they possess in order to not reveal it and cut back its worth. An on a regular basis instance happens within the recreation of poker, the place gamers bluff with a view to conceal details about their playing cards.

According to Farina, “we now live in a world in which machines are far better at bluffing than humans.”

A state of affairs with “massive amounts of imperfect information,” has introduced Farina again to his board-game beginnings. Stratego is a army technique recreation that has impressed analysis efforts costing tens of millions of {dollars} to provide techniques able to beating human gamers. Requiring advanced danger calculation and misdirection, or bluffing, it was presumably the one classical recreation for which main efforts had failed to provide superhuman efficiency, Farina says.

With new algorithms and coaching costing lower than $10,000, moderately than tens of millions, Farina and his analysis crew have been in a position to beat one of the best participant of all time — with 15 wins, 4 attracts, and one loss. Farina says he’s thrilled to have produced such outcomes so economically, and he hopes “these new techniques will be incorporated into future pipelines,” he says.

“We have seen constant progress towards constructing algorithms that can reason strategically and make sound decisions despite large action spaces or imperfect information. I am excited about seeing these algorithms incorporated into the broader AI revolution that’s happening around us.”