Sakhanda Wire
NVDA $152.94 -2.05% MSFT $505.64 -2.38% GOOGL $280.11 -1.27% META $619.47 -1.11% AMZN $256.54 -0.47%
← Back to the news

Ataraxos defeats elite human player in long-standing Stratego challenge

A research team from Carnegie Mellon, MIT, New York University, and Stanford University has developed an AI system that can defeat top human Stratego players. Called Ataraxos, it beat Pim Niemeijer, widely regarded as one of the strongest Stratego players ever, by 15 games to one, with four draws. The system was trained using 16 GPUs and a budget of a few thousand dollars.

Stratego is difficult for computers because players can see the positions of opposing pieces but not their identities. Each side controls 40 pieces representing military ranks, along with bombs and a flag. The objective is to capture the opponent’s flag. A piece’s identity becomes known only when it meets another piece in battle; the weaker piece is removed and the winner’s identity is disclosed.

The researchers’ approach included a second neural network designed to estimate which hidden pieces the opponent might hold. Eugene Vinitsky of New York University, a study co-author, said Stratego combines extensive hidden information with decisions that unfold over a long period. Earlier systems had mastered games such as chess, Go, and poker, but had not reliably surpassed the best Stratego players.

Written by Sakhanda Wire AI from reporting by Ars Technica. Facts, quotes and full context are in the original article below.

Originally published by Ars Technica on

Read the original on Ars Technica ↗

The reporting and the image belong to Ars Technica and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news