Work

Personalized Help for Optimizing Low-Skilled Users' Strategy

Year: 2024

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2411.09109

Authors: Gu, Feng, Wongkamjan, Wichayaporn, Kummerfeld, Jonathan K., Peskoff, Denis, May, Jonathan, Boyd-Graber, Jordan

Institutions: University of Maryland, College Park, The University of Sydney, Princeton University, University of Southern California

Language: English

Topic: Artificial Intelligence in Games

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, University of Southern California, Defense Advanced Research Projects Agency, Advanced Research Projects Agency

Award: Computing Innovation Fellows Project 2021

OpenAlex ID: W4404450389

Cites:

Cited by:

Related to: 10