Feasible Action-Space Reduction as a Metric of Causal Responsibility in Multi-Agent Spatial Interactions

TL;DR

This paper introduces FeAR, a novel metric based on feasible action space reduction, to quantify causal responsibility in multi-agent spatial interactions like traffic, integrating ethical concepts with practical simulation results.

Contribution

It proposes a new responsibility metric tailored for spatial interactions, grounded in ethical and philosophical concepts, and demonstrates its application in simulations of complex multi-agent scenarios.

Findings

FeAR effectively quantifies responsibility based on action space reduction.

Norms and context significantly influence responsibility attribution.

The metric can be applied to complex multi-agent interactions for safety assessment.

Abstract

Modelling causal responsibility in multi-agent spatial interactions is crucial for safety and efficiency of interactions of humans with autonomous agents. However, current formal metrics and models of responsibility either lack grounding in ethical and philosophical concepts of responsibility, or cannot be applied to spatial interactions. In this work we propose a metric of causal responsibility which is tailored to multi-agent spatial interactions, for instance interactions in traffic. In such interactions, a given agent can, by reducing another agent's feasible action space, influence the latter. Therefore, we propose feasible action space reduction (FeAR) as a metric of causal responsibility among agents. Specifically, we look at ex-post causal responsibility for simultaneous actions. We propose the use of Moves de Rigueur (MdR) - a consistent set of prescribed actions for agents - to model the effect of norms on responsibility allocation. We apply the metric in a grid world simulation for spatial interactions and show how the actions, contexts, and norms affect the causal responsibility ascribed to agents. Finally, we demonstrate the application of this metric in complex multi-agent interactions. We argue that the FeAR metric is a step towards an interdisciplinary framework for quantifying responsibility that is needed to ensure safety and meaningful human control in human-AI systems.