AI for Explaining Decisions in Multi-Agent Environments
This addresses the problem of human trust and acceptance in complex AI systems for users in multi-agent settings, but it is incremental as it reviews existing work and outlines future directions without presenting new results.
The paper tackles the challenge of explaining AI decisions in multi-agent environments where goals are unknown, proposing a new research direction called xMASE to increase user satisfaction by considering factors like fairness and privacy.
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.