Recent advancements in artificial intelligence (AI) have leveraged large-scale games as benchmarks to gauge progress, with AI now frequently outperforming human capabilities. Traditionally, this success has largely relied on solving Nash equilibrium (NE) using variations of the counterfactual regret minimization (CFR) method in games with incomplete information. However, the variety of Nash equilibria has been largely overlooked in previous research, limiting the adaptability of AI to meet diverse human preferences. To address this challenge, where AI is powerful but struggles to meet customization needs, we introduce a novel approach: Preference-CFR, which incorporates two new parameters: preference degree and vulnerability degree. These parameters allow for greater flexibility in AI strategy development without compromising convergence. Our method significantly alters the distribution of final strategies, enabling the creation of customized AI models that better align with individual user needs. Using Texas Holdém as a case study, our experiments demonstrate how Preference CFR can be adjusted to either emphasize customization, prioritizing user preferences, or to enhance performance, striking a balance between the depth of customization and strategic optimality.
View on arXiv