Personalized Help for Optimizing Low-Skilled Users' Strategy

TL;DR

This paper enhances a natural language agent to provide personalized move and message advice in Diplomacy, demonstrating that such advice can help low-skilled players improve and sometimes outperform experienced players, even when not followed.

Contribution

It introduces a personalized advice system for Diplomacy that benefits low-skilled players and explores the impact of advice presence and adherence.

Findings

Advice improves novice performance

Advice presence benefits players regardless of following it

Some advice helps novices surpass experienced players

Abstract

AIs can beat humans in game environments; however, how helpful those agents are to human remains understudied. We augment CICERO, a natural language agent that demonstrates superhuman performance in Diplomacy, to generate both move and message advice based on player intentions. A dozen Diplomacy games with novice and experienced players, with varying advice settings, show that some of the generated advice is beneficial. It helps novices compete with experienced players and in some instances even surpass them. The mere presence of advice can be advantageous, even if players do not follow it.