Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems
Provides a principled method for responsibility attribution in multi-agent systems, addressing a fundamental challenge for designers and analysts.
This work introduces a counterfactual notion of responsibility for agents in probabilistic multi-agent systems, using Shapley value to allocate accountability fairly. It provides a formal framework for verification and strategic reasoning, and demonstrates computation of Nash equilibrium profiles that balance responsibility and expected reward.
Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analysis of multi-agent systems. In this work, we model such systems as concurrent stochastic multi-player games and introduce a notion of retrospective (backward) counterfactual responsibility, which quantifies an agent's accountability for outcomes resulting from a given strategy profile. To allocate responsibility among agents, we utilise the Shapley value and formally show that this method satisfies key desirable properties, including fairness and consistency. Building on this foundation, we propose a formal framework that supports both verification and strategic reasoning in responsibility-aware multi-agent systems. Furthermore, by adopting Nash equilibrium as the solution concept, we demonstrate how to compute stable strategy profiles in which agents trade off responsibility against expected reward.