Distinguishing humans from computers in the game of go: a complex network approach

TL;DR

This paper uses complex network analysis to differentiate between human and computer gameplay in go, revealing statistically significant differences that can serve as a Turing-like test for go-playing algorithms.

Contribution

It introduces a novel network-based method to distinguish human from computer go games, including the ability to identify deterministic versus stochastic computer algorithms.

Findings

Statistical features differ significantly between human and computer networks.

Differences are detectable with relatively small game datasets.

The method can identify the nature of computer algorithms (deterministic or stochastic).

Abstract

We compare complex networks built from the game of go and obtained from databases of human-played games with those obtained from computer-played games. Our investigations show that statistical features of the human-based networks and the computer-based networks differ, and that these differences can be statistically significant on a relatively small number of games using specific estimators. We show that the deterministic or stochastic nature of the computer algorithm playing the game can also be distinguished from these quantities. This can be seen as tool to implement a Turing-like test for go simulators.