Instilling moral value alignment by means of multi-objective reinforcement learning

AI research is being challenged with ensuring that autonomous agents learn to behave ethically, namely in alignment with moral values. Here, we propose a novel way of tackling the value alignment problem as a two-step process. The first step consists on formalising moral values and value aligned beh...

Descripción completa

Detalles Bibliográficos
Autores: Rodríguez-Soto, Manel, Serramia, Marc, López-Sánchez, Maite, Rodríguez-Aguilar, Juan Antonio
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/282390
Acceso en línea:http://hdl.handle.net/10261/282390
https://api.elsevier.com/content/abstract/scopus_id/85124018759
Access Level:acceso abierto
Palabra clave:Ethics
Multi-objective reinforcement learning
Reinforcement learning
Value alignment
Descripción
Sumario:AI research is being challenged with ensuring that autonomous agents learn to behave ethically, namely in alignment with moral values. Here, we propose a novel way of tackling the value alignment problem as a two-step process. The first step consists on formalising moral values and value aligned behaviour based on philosophical foundations. Our formalisation is compatible with the framework of (Multi-Objective) Reinforcement Learning, to ease the handling of an agent’s individual and ethical objectives. The second step consists in designing an environment wherein an agent learns to behave ethically while pursuing its individual objective. We leverage on our theoretical results to introduce an algorithm that automates our two-step approach. In the cases where value-aligned behaviour is possible, our algorithm produces a learning environment for the agent wherein it will learn a value-aligned behaviour.