Feasible Action Space Reduction for Quantifying Causal Responsibility in Continuous Spatial Interactions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: George, Ashwin, Siebert, Luciano Cavalcante, Abbink, David A., Zgonnikov, Arkady
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912389595660288
author George, Ashwin
Siebert, Luciano Cavalcante
Abbink, David A.
Zgonnikov, Arkady
author_facet George, Ashwin
Siebert, Luciano Cavalcante
Abbink, David A.
Zgonnikov, Arkady
contents Understanding the causal influence of one agent on another agent is crucial for safely deploying artificially intelligent systems such as automated vehicles and mobile robots into human-inhabited environments. Existing models of causal responsibility deal with simplified abstractions of scenarios with discrete actions, thus, limiting real-world use when understanding responsibility in spatial interactions. Based on the assumption that spatially interacting agents are embedded in a scene and must follow an action at each instant, Feasible Action-Space Reduction (FeAR) was proposed as a metric for causal responsibility in a grid-world setting with discrete actions. Since real-world interactions involve continuous action spaces, this paper proposes a formulation of the FeAR metric for measuring causal responsibility in space-continuous interactions. We illustrate the utility of the metric in prototypical space-sharing conflicts, and showcase its applications for analysing backward-looking responsibility and in estimating forward-looking responsibility to guide agent decision making. Our results highlight the potential of the FeAR metric for designing and engineering artificial agents, as well as for assessing the responsibility of agents around humans.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17739
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feasible Action Space Reduction for Quantifying Causal Responsibility in Continuous Spatial Interactions
George, Ashwin
Siebert, Luciano Cavalcante
Abbink, David A.
Zgonnikov, Arkady
Multiagent Systems
Computers and Society
Human-Computer Interaction
Robotics
Understanding the causal influence of one agent on another agent is crucial for safely deploying artificially intelligent systems such as automated vehicles and mobile robots into human-inhabited environments. Existing models of causal responsibility deal with simplified abstractions of scenarios with discrete actions, thus, limiting real-world use when understanding responsibility in spatial interactions. Based on the assumption that spatially interacting agents are embedded in a scene and must follow an action at each instant, Feasible Action-Space Reduction (FeAR) was proposed as a metric for causal responsibility in a grid-world setting with discrete actions. Since real-world interactions involve continuous action spaces, this paper proposes a formulation of the FeAR metric for measuring causal responsibility in space-continuous interactions. We illustrate the utility of the metric in prototypical space-sharing conflicts, and showcase its applications for analysing backward-looking responsibility and in estimating forward-looking responsibility to guide agent decision making. Our results highlight the potential of the FeAR metric for designing and engineering artificial agents, as well as for assessing the responsibility of agents around humans.
title Feasible Action Space Reduction for Quantifying Causal Responsibility in Continuous Spatial Interactions
topic Multiagent Systems
Computers and Society
Human-Computer Interaction
Robotics
url https://arxiv.org/abs/2505.17739