Social World Model-Augmented Mechanism Design Policy Learning

TL;DR

This paper introduces SWM-AP, a hierarchical social world model that improves mechanism design in multi-agent systems by inferring agent traits and enhancing policy learning efficiency through simulation and online inference.

Contribution

The paper presents a novel hierarchical social world model that infers agent traits and boosts mechanism design policy learning in complex multi-agent environments.

Findings

SWM-AP outperforms baselines in diverse multi-agent tasks.

Enhanced sample efficiency in mechanism design.

Effective trait inference from interaction trajectories.

Abstract

Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits (e.g., skills, preferences) and dealing with complex multi-agent system dynamics. These challenges are compounded by the critical need for high sample efficiency due to costly real-world interactions. World Models, by learning to predict environmental dynamics, offer a promising pathway to enhance mechanism design in heterogeneous and complex systems. In this paper, we introduce a novel method named SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically modeling agents' behavior to enhance mechanism design. Specifically, the social world model infers agents' traits from their interaction trajectories and learns a trait-based model to predict agents' responses to the deployed mechanisms. The mechanism design policy collects extensive training trajectories by interacting with the social world model, while concurrently inferring agents' traits online during real-world interactions to further boost policy learning efficiency. Experiments in diverse settings (tax policy design, team coordination, and facility location) demonstrate that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.