Generative Modeling of Individual Behavior at Scale

TL;DR

This paper introduces a scalable, generative approach to model and manipulate individual human behavior using style vectors learned through multi-task learning and parameter-efficient fine-tuning, applicable across games and image generation.

Contribution

It presents a novel method for modeling individual behavior with generative style vectors, enabling scalable, interpretable, and steerable behavior synthesis across diverse domains.

Findings

Successfully modeled 47,864 chess players and 2,000 Rocket League players.

Demonstrated style steering in games and image generation.

Achieved scalable, interpretable individual behavior modeling.

Abstract

There has been a growing interest in using AI to model human behavior, particularly in domains where humans interact with this technology. While most existing work models human behavior at an aggregate level, our goal is to model behavior at the individual level. Recent approaches to behavioral stylometry -- or the task of identifying a person from their actions alone -- have shown promise in domains like chess, but these approaches are either not scalable (e.g., fine-tune a separate model for each person) or not generative, in that they cannot generate actions. We address these limitations by framing behavioral stylometry as a multi-task learning problem -- where each task represents a distinct person -- and use parameter-efficient fine-tuning (PEFT) methods to learn an explicit style vector for each person. Style vectors are generative: they selectively activate shared "skill" parameters to generate actions in the style of each person. They also induce a latent space that we can interpret and manipulate algorithmically. In particular, we develop a general technique for style steering that allows us to steer a player's style vector towards a desired property. We apply our approach to two very different games, at unprecedented scales: chess (47,864 players) and Rocket League (2,000 players). We also show generality beyond gaming by applying our method to image generation, where we learn style vectors for 10,177 celebrities and use these vectors to steer their images.