Partial Observability Approach for the Optimal Transparency Problem in Multi-agent Systems

TL;DR

This paper explores how a principal can optimize multi-agent network performance by controlling information sharing through partial observability, using static partitions and analyzing steady-state behaviors.

Contribution

It introduces a novel partial observability framework with static agent partitions and provides an efficient algorithm for optimizing these partitions based on steady-state analysis.

Findings

Optimal partitions improve network performance metrics.

The proposed algorithm efficiently finds near-optimal information structures.

Numerical examples validate the effectiveness of the approach.

Abstract

This paper considers a network of agents, where each agent is assumed to take actions optimally with respect to a predefined payoff function involving the latest actions of the agent's neighbors. Neighborhood relationships stem from payoff functions rather than actual communication channels between the agents. A principal is tasked to optimize the network's performance by controlling the information available to each agent with regard to other agents' latest actions. The information control by the principal is done via a partial observability approach, which comprises a static partitioning of agents into blocks and making the mean of agents' latest actions within each block publicly available. While the problem setup is general in terms of the payoff functions and the network's performance metric, this paper has a narrower focus to illuminate the problem and how it can be addressed in practice. In particular, the performance metric is assumed to be a function of the steady-state behavior of the agents. After conducting a comprehensive steady-state analysis of the network, an efficient algorithm finding optimal partitions with respect to various performance metrics is presented and validated via numerical examples.