Diversifying Agent's Behaviors in Interactive Decision Models

TL;DR

This paper introduces a method for diversifying the modeled behaviors of other agents in decision-making processes, enhancing robustness in uncertain and privacy-sensitive multi-agent environments.

Contribution

It proposes a novel approach to generate diverse agent behaviors from known behaviors using feature expansion and diversity metrics, improving decision models in open AI systems.

Findings

Effective behavior diversification improves decision robustness.

Method outperforms baseline models in two problem domains.

Enhances modeling of unknown or hidden agent behaviors.

Abstract

Modelling other agents' behaviors plays an important role in decision models for interactions among multiple agents. To optimise its own decisions, a subject agent needs to model what other agents act simultaneously in an uncertain environment. However, modelling insufficiency occurs when the agents are competitive and the subject agent can not get full knowledge about other agents. Even when the agents are collaborative, they may not share their true behaviors due to their privacy concerns. In this article, we investigate into diversifying behaviors of other agents in the subject agent's decision model prior to their interactions. Starting with prior knowledge about other agents' behaviors, we use a linear reduction technique to extract representative behavioral features from the known behaviors. We subsequently generate their new behaviors by expanding the features and propose two diversity measurements to select top-K behaviors. We demonstrate the performance of the new techniques in two well-studied problem domains. This research will contribute to intelligent systems dealing with unknown unknowns in an open artificial intelligence world.