TY - GEN
T1 - Feasible Action-Space Reduction as a Metric of Causal Responsibility in Multi-Agent Spatial Interactions
AU - George, Ashwin
AU - Cavalcante Siebert, Luciano
AU - Abbink, David
AU - Zgonnikov, Arkady
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85175829522&partnerID=8YFLogxK
U2 - 10.3233/FAIA230349
DO - 10.3233/FAIA230349
M3 - Conference contribution
AN - SCOPUS:85175829522
SN - 978-1-64368-436-9
T3 - Frontiers in Artificial Intelligence and Applications
SP - 819
EP - 826
BT - ECAI 2023 - 26th European Conference on Artificial Intelligence, including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023 - Proceedings
A2 - Gal, Kobi
A2 - Nowe, Ann
A2 - Nalepa, Grzegorz J.
A2 - Fairstein, Roy
A2 - Radulescu, Roxana
PB - IOS Press
T2 - 26th European Conference on Artificial Intelligence, ECAI 2023
Y2 - 30 September 2023 through 4 October 2023
ER -