Meta Researchers Create AI That Masters Diplomacy, Fooling Human Players

According to Meta, the answer is yes. Cicero learned his skills by playing an online version of Diplomacy at webDiplomacy.net. Over time, he became a master of the game, reaching "more than double the average score" of human gamers and ranking in the top 10% of people who played more than one game.

To create Cicero, Meta gathered AI models for strategic reasoning (similar to AlphaGo) and natural language processing (similar to GPT-3) and bundled them into a single agent. During each game, Cicero examines the state of the game board and the chat history and predicts how the other players will act. He formulates a plan which he executes through a language model that can generate human-like dialogue, allowing him to coordinate with other players.

Enlarge / A block diagram of Cicero, the diplomacy bot, provided by Meta. Meta AI

Meta calls Cicero's natural language skills a "controllable dialogue pattern", which is central to Cicero's personality. Like GPT-3, Cicero draws from a large corpus of Internet text extracted from the web. "To create a controllable dialog model, we started with a 2.7 billion parameter BART-like language model pre-trained on text from the internet and refined on over 40,000 human games on webDiplomacy.net ", writes Meta.

The resulting model mastered the intricacies of a complex game. "Cicero can deduce, for example, that later in the game he will need the support of a...