Explainability in autonomous pedagogically structured scenarios
This work addresses the lack of research on inter-agent explainability in autonomous systems, which is crucial for improving communication and trust between pedagogical teachers and learners in partially observable environments.
The paper tackles the problem of explainability in multi-agent systems within pedagogically structured environments, where partial observability and incomplete awareness of states and beliefs make it challenging for agents to explain decisions to each other, and it emphasizes the need for robust, iterative explanation-based communication to build trust and reliability.
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.