AI Seminar - Blameworthiness in Multi-Agent Settings

AAAI Practice Presentation

Title: Blameworthiness in Multi-Agent Settings

Abstract: As we move towards an era where autonomous systems are ubiquitous, being able to reason formally about moral responsibility will become more and more critical.  In this talk I will present recent work on providing 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.