Blameworthiness in Multi-Agent Settings

TL;DR

This paper formalizes the concept of blameworthiness in multi-agent systems, proposing a method to assign blame to groups and individuals based on causal models and cooperative game theory, which is crucial for ethical autonomous agents.

Contribution

It introduces a formal framework for blameworthiness in multi-agent settings and adapts the Shapley value to attribute blame to individuals from group blame assessments.

Findings

Provides a method for ascribing blameworthiness to groups based on causal models.

Extends group blameworthiness to individuals using the Shapley value.

Lays groundwork for morally responsible autonomous agents.

Abstract

We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a distribution over causal models that describe how the outcome might arise). We then show how we can go from an ascription of blameworthiness for groups to an ascription of blameworthiness for individuals using a standard notion from cooperative game theory, the Shapley value. We believe that getting a good notion of blameworthiness in a group setting will be critical for designing autonomous agents that behave in a moral manner.