AI for Explaining Decisions in Multi-Agent Environments

TL;DR

This paper introduces a new research direction, xMASE, focused on generating explanations in multi-agent AI environments to enhance user satisfaction by considering various preferences and fairness aspects.

Contribution

The paper proposes xMASE, a novel research framework for explanation generation in multi-agent settings, and reviews current methods and future research directions.

Findings

Review of existing explanation methods in multi-agent environments

Identification of challenges in increasing user satisfaction

Proposal of research directions for efficient explanation algorithms

Abstract

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: xMASE. We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI system's decisions in multi-agent environments.