Personalized Help for Optimizing Low-Skilled Users' Strategy
This addresses the issue of low-skilled users struggling in complex games, though it is incremental as it builds on an existing agent.
The study tackled the problem of AI agents being unhelpful to humans by augmenting CICERO to provide move and message advice based on player intentions in Diplomacy, resulting in novices competing with or surpassing experienced players in some cases.
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.