Combining Theory of Mind and Abduction for Cooperation under Imperfect Information

TL;DR

This paper introduces a novel agent model that combines Theory of Mind and abductive reasoning to enhance cooperation under imperfect information, demonstrated through successful implementation in the game Hanabi.

Contribution

It presents a domain-independent framework integrating Theory of Mind and abductive reasoning for cooperative decision-making under uncertainty.

Findings

Effective cooperation in Hanabi using the model

Successful implementation of the combined approach

Demonstrated domain independence

Abstract

In this paper, we formalise and implement an agent model for cooperation under imperfect information. It is based on Theory of Mind (the cognitive ability to understand the mental state of others) and abductive reasoning (the inference paradigm that computes explanations from observations). The combination of these two techniques allows agents to derive the motives behind the actions of their peers, and incorporate this knowledge into their own decision-making. We have implemented this model in a totally domain-independent fashion and successfully tested it for the cooperative card game Hanabi.