Search Meta's board game-playing AI can pass as a human in game negotiations An AI developed by researchers at Meta convincingly negotiated with humans while playing an online version of the board game Diplomacy. It was also ranked in the top 10 per cent of players Technology 22 November 2022 Diplomacy is a first world war strategy game Alamy Stock Photo An AI that is an expert player of the first world war strategy game Diplomacy can now participate in game conversations and negotiations without most human players realising they are talking to a machine. The game of Diplomacy involves seven players competing for control over European territories. But there is also room for cooperation as players negotiate temporary alliances in coordinating movements and attacks. Researchers at Meta, the parent company to Facebook, built an AI named Cicero that learned to play Diplomacy through trial and error and by partially mimicking what human players typically do.

Players have often used KataGo to test their skills, train for other matches, and even analyze past games, yet in a study posted recently on the preprint server arXiv, researchers report that by using an adversarial policy--a kind of machine-learning algorithm built to attack or learn weaknesses in other systems--they've been able to beat KataGo at its own game between 50 to 99 percent of the time, depending on how much "thinking ahead" the AI does. "KataGo is able to recognize that passing would result in a forced win by our adversary, but given a low tree-search budget it does not have the foresight to avoid this," co-author Tony Wang, a Ph.D. student at MIT said of the study on the site LessWrong, an online community dedicated to "causing safe and beneficial AI."

Learning to play Diplomacy is a big deal for several reasons. Not only does it involve multiple players, who make moves at the same time, but each turn is preceded by a brief negotiation in which players chat in pairs in an attempt to form alliances or gang up on rivals. After this round of negotiation, players then decide what pieces to move--and whether to honor or renege on a deal. At each point in the game, Cicero models how the other players are likely to act based on the state of the board and its previous conversations with them. It then figures out how players can work together for mutual benefit and generates messages designed to achieve those aims. To build Cicero, Meta marries two different types of AI: a reinforcement learning model that figures out what moves to make, and a large language model that negotiates with other players.

"This is a really amazing result," says François Le Gall, a mathematician at Nagoya University in Japan, who was not involved in the work. "Matrix multiplication is used everywhere in engineering," he says. "Anything you want to solve numerically, you typically use matrices." Despite the calculation's ubiquity, it is still not well understood. A matrix is simply a grid of numbers, representing anything you want.

While games have been used extensively as milestones to evaluate game-playing AI, there exists no standardised framework for reporting the obtained observations. As a result, it remains difficult to draw general conclusions about the strengths and weaknesses of different game-playing AI algorithms. In this paper, we propose reporting guidelines for AI game-playing performance that, if followed, provide information suitable for unbiased comparisons between different AI approaches. The vision we describe is to build benchmarks and competitions based on such guidelines in order to be able to draw more general conclusions about the behaviour of different AI algorithms, as well as the types of challenges different games pose.