The machine called DeepRole is the first gaming bot that can win online multiplayer games in which the participants' team allegiances are initially unclear, according to a news release by MIT on Wednesday.

Previously, several bots have been built to beat professional players but the bot knows its opponents and teammates from the start.

The bot is designed with novel "deductive reasoning" in its AI algorithm, enabling it to reason about partially observable actions to quickly learn whom to ally with and which actions to take to ensure its team's victory.

The researchers pitted DeepRole against human players in more than 4,000 rounds of the online game "The Resistance: Avalon," a game of imperfect information. In this game, players try to deduce their peers' secret roles as the game progresses, while simultaneously hiding their own roles.

The bot is trained by playing against itself as both resistance and spy. When playing an online game, it uses its game tree to estimate what each player is going to do and a high probability for each player's role. Simultaneously, it uses this same technique to estimate how a third-person observer might interpret its own actions.

DeepRole consistently outperformed human players as both a teammate and an opponent, according to MIT.

"Avalon" enables players to chat on a text module during the game, but the bot did not need to communicate with other players. Next, the researchers may enable the bot to communicate during games with simple text, such as saying a player is good or bad.

The work is part of a broader project to better model how humans make socially informed decisions.