A Game-Theoretic Account of Responsibility Allocation

TL;DR

This paper introduces a game-theoretic framework for responsibility attribution in multi-agent systems, distinguishing between forward and backward responsibility, and incorporating strategic, causal, and quantitative aspects, with connections to existing models.

Contribution

It formalizes responsibility notions in extensive form games, linking forward and backward responsibility, and integrates cooperative game theory for quantitative responsibility assessment.

Findings

Defines forward and backward responsibility in game-theoretic terms

Establishes formal connections between responsibility notions under perfect recall

Demonstrates the framework's ability to encompass prior responsibility models

Abstract

When designing or analyzing multi-agent systems, a fundamental problem is responsibility ascription: to specify which agents are responsible for the joint outcome of their behaviors and to which extent. We model strategic multi-agent interaction as an extensive form game of imperfect information and define notions of forward (prospective) and backward (retrospective) responsibility. Forward responsibility identifies the responsibility of a group of agents for an outcome along all possible plays, whereas backward responsibility identifies the responsibility along a given play. We further distinguish between strategic and causal backward responsibility, where the former captures the epistemic knowledge of players along a play, while the latter formalizes which players -- possibly unknowingly -- caused the outcome. A formal connection between forward and backward notions is established in the case of perfect recall. We further ascribe quantitative responsibility through cooperative game theory. We show through a number of examples that our approach encompasses several prior formal accounts of responsibility attribution.