English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Modelling causal responsibility in multi-agent spatial interactions iscrucial for safety and efficiency of interactions of humans with autonomousagents. However, current formal metrics and models of responsibility eitherlack grounding in ethical and philosophical concepts of responsibility, orcannot be applied to spatial interactions. In this work we propose a metric ofcausal 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 ofcausal responsibility among agents. Specifically, we look at ex-post causalresponsibility for simultaneous actions. We propose the use of Moves de Rigueur(MdR) - a consistent set of prescribed actions for agents - to model the effectof norms on responsibility allocation. We apply the metric in a grid worldsimulation for spatial interactions and show how the actions, contexts, andnorms affect the causal responsibility ascribed to agents. Finally, wedemonstrate the application of this metric in complex multi-agent interactions.We argue that the FeAR metric is a step towards an interdisciplinary frameworkfor quantifying responsibility that is needed to ensure safety and meaningfulhuman control in human-AI systems.

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