Simanaitis Says

On cars, old, new and future; science & technology; vintage airplanes, computer flight simulation of them; Sherlockiana; our English language; travel; and other stuff

A.I. LEARNS THE DIPLOMACY GAME

MACHINE-LEARNING ARTIFICIAL intelligence (A.I.) has already beat humans in playing chess, Go, and poker. But what about a board game that involves negotiation and even deception? The classic board game Diplomacy presents such confrontation.

This board game was created by Allan B. Calhamer in 1954; it was released commercially in 1959. Fans of the game included John F. Kennedy, Henry Kissinger, and broadcast journalist Walter Cronkite. Diplomacy, Wikipedia notes, differs from most board wargames “in forming and betraying alliances with other players and forming beneficial strategies.”  

And in Science, November 25, 2022, Matthew Hutson writes, “Now, an A.I. algorithm from the company Meta has shown it can beat many humans in the board game Diplomacy.”

Diplomacy, an Art. Matthew Hutson writes, “Diplomacy, many a statesperson has argued, is an art: one that requires not just strategy, but also intuition, persuasion, and even subterfuge—human skills that have long been off-limits to even the most powerful artificial intelligence (AI) approaches.”

Formerly Facebook, Meta Platforms is an American multinational technology conglomerate based in Menlo Park, California.

Hutson describes, “Meta’s AI agent, CICERO, welds together a strategic reasoning module and a dialogue module. As in other machine learning AIs, the modules were trained on large data sets, in this case 125,261 games that humans had played online—both the game plays and transcripts of player negotiations.”

“To test its skill,” Hutson says, “the researchers had CICERO play 40 online games against humans (who mostly assumed it was a human). It placed in the top 10% of players who’d played at least two games. ‘In a game that involves language and negotiation, that agents can reach human parity is very exciting,’ says Zhou Yu, a computer scientist at Columbia University who studies dialogue systems.”

Hutson also cites Jonathan Gratch, a computer scientist at the University of Southern California who notes two technical innovations. “First, CICERO grounds its communication in multistep planning, and second, it keeps its remarks and game play within the realm of human convention.”

Image from Science, November 25, 2022.

“During training,” Hutson says, “the researchers also rewarded it for humanlike play so that its actions wouldn’t confound other players. In any domain, whether dinner-table manners or driving, conventions tend to ease interactions.”

Hutson continues: “Gratch says the work is ‘impressive’ and ‘important.’ But he questions how much CICERO’s dialogue, as opposed to its strategic planning, contributed to its success. According to the paper, Diplomacy experts rated about 10% of CICERO’s messages as inconsistent with its plan or game state. ‘That suggests it’s saying a lot of crap,’ Gratch says. Yu agrees, noting that CICERO sometimes utters non sequiturs.”

Geez. Now and again, so do I. ds 

© Dennis Simanaitis, SimanaitisSays.com, 2022

One comment on “A.I. LEARNS THE DIPLOMACY GAME

  1. Eric
    December 9, 2022

    Reblogged this on Calculus of Decay .

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: