spot_img
Thursday, December 1, 2022
HomeTechnologyAI system beat humans in strategy game Diplomacy

AI system beat humans in strategy game Diplomacy

-

- Advertisement -

Unlike chess, games like Diplomacy are considered more difficult for an “intelligent” machine because they require the ability to negotiate and communicate with teammates.

A new artificial intelligence system named Cicero has become so “expert” at the challenging online strategy and diplomatic negotiation board game Diplomacy that it has beaten human players, a feat that has been achieved for the first time.

- Advertisement -

Playing anonymously against humans in 40 online games of a Diplomacy “tournament” between August and October 2022, Cicero achieved more than twice the “score” on average (25.8%) than humans (12.4%).

Cicero “passed” as human to all 82 human players it faced, none of whom realized it was playing an AI program rather than a human. They found out afterwards and of course were surprised. Only one mentioned (after…holiday) that he had some suspicions that one of his teammates was not human.

- Advertisement -

The researchers of the Meta Fundamental AI Research (FAIR) unit – the research arm of Facebook’s parent Meta in the field of artificial intelligence – in collaboration with experts from leading American universities (MIT, Harvard, Stanford, Columbia, California-Berkeley, Carnegie-Mellon ), made the relevant publication in the journal “Science”.

Although AI has so far shown considerable success and wins over humans in competitive two-player games such as chess and Go, which do not require communication with others, games such as Diplomacy are considered more difficult for a “smart” engine, because they require the ability to negotiate with teammates in natural language, cooperation, multi-level competition with more than one player at the same time, moves involving dishonesty and bluffing, etc.

The new system developed by the FAIR team has two subsystems: a dialogic one and a strategic reasoning one. Thanks to its new learning algorithms, it is not only capable of mimicking natural language, but – even more importantly – it can analyze the goals, beliefs and intentions of the seven human teammates based on their movements on the game map, then using this information to draw up a strategic plan of action that takes into account the diverse and often conflicting interests to propose a coordination based on mutual benefit.

- Advertisement -
spot_img
Terrance
Terrance
I am Terrance Carlson, author at News Bulletin 247. I mostly cover technology news and I have been working in this field for a long time. I have a lot of experience and I am highly knowledgeable in this area. I am a very reliable source of information and I always make sure to provide accurate news to my readers.

Related articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Stay Connected

1,250FansLike
1,500FollowersFollow

Latest posts