Understanding each other is the key to success in collaboration. For humans, attributing mental states to others, the theory of mind, provides the crucial advantage. We argue for formulating human--AI interaction as a multi-agent problem, endowing AI with a computational theory of mind to understand and anticipate the user. To differentiate the approach from previous work, we introduce a categorisation of user modelling approaches based on the level of agency learnt in the interaction. We describe our recent work in using nested multi-agent modelling to formulate user models for multi-armed bandit based interactive AI systems, including a proof-of-concept user study.
@article{arxiv.1912.05284,
title = {Interactive AI with a Theory of Mind},
author = {Mustafa Mert Çelikok and Tomi Peltola and Pedram Daee and Samuel Kaski},
journal= {arXiv preprint arXiv:1912.05284},
year = {2019}
}
Comments
This is a slightly updated version of a manuscript that appeared in ACM CHI 2019 Workshop: Computational Modeling in Human-Computer Interaction