Personalized Help for Optimizing Low-Skilled Users' Strategy
Gu, Feng, Wongkamjan, Wichayaporn, Boyd-Graber, Jordan Lee, Kummerfeld, Jonathan K., Peskoff, Denis, May, Jonathan
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Nov-13-2024
- Country:
- Asia (0.71)
- Europe (1.00)
- North America > United States
- New York (0.16)
- Genre:
- Questionnaire & Opinion Survey (0.46)
- Research Report (0.50)
- Industry:
- Education (1.00)
- Information Technology (0.88)
- Leisure & Entertainment > Games
- Computer Games (0.88)
- Technology:
- Information Technology > Artificial Intelligence
- Games (0.93)
- Issues > Social & Ethical Issues (0.47)
- Machine Learning (1.00)
- Natural Language (1.00)
- Representation & Reasoning (0.94)
- Information Technology > Artificial Intelligence