Explainability in autonomous pedagogically structured scenarios

TL;DR

This paper explores the concept of explainability in autonomous multi-agent systems within pedagogically structured environments, emphasizing the importance of transparent communication between agents to enhance trust and reliability.

Contribution

It introduces the notion of explainability specifically for decision-making processes in pedagogically structured autonomous environments, highlighting the need for inter-agent explanation mechanisms.

Findings

Explainability is crucial for trust in multi-agent pedagogical systems.

Current research mainly focuses on explanations to humans, with less on inter-agent explainability.

Robust, iterative explanation-based communication improves agent cooperation.

Abstract

We present the notion of explainability for decision-making processes in a pedagogically structured autonomous environment. Multi-agent systems that are structured pedagogically consist of pedagogical teachers and learners that operate in environments in which both are sometimes not fully aware of all the states in the environment and beliefs of other agents thus making it challenging to explain their decisions and actions with one another. This work emphasises the need for robust and iterative explanation-based communication between the pedagogical teacher and the learner. Explaining the rationale behind multi-agent decisions in an interactive, partially observable environment is necessary to build trustworthy and reliable communication between pedagogical teachers and learners. Ongoing research is primarily focused on explanations of the agents' behaviour towards humans, and there is a lack of research on inter-agent explainability.