Automated Ethical Design of Multi-Agent Reinforcement Learning Environments

Proceedings of the 27th International Conference of the Catalan Association for Artificial Intelligence. The International Conference of the Catalan Association for Artificial Intelligence (CCIA) is a well-established annual event that brings together researchers in Artificial Intelligence from acro...

ver descrição completa

Detalhes bibliográficos
Autores: Mayoral-Macau, Arnau, Rodríguez-Soto, Manel, Marchesini, Enrico, López-Sánchez, Maite, Sánchez-Fibla, Martí, Farinelli, Alessandro, Rodríguez-Aguilar, Juan Antonio
Formato: otro
Estado:Versión publicada
Fecha de publicación:2025
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:dnet:digitalcsic_::a33331e2aa524ff921c8cccb994006c9
Acesso em linha:http://hdl.handle.net/10261/429982
https://api.elsevier.com/content/abstract/scopus_id/105021088513
Access Level:acceso abierto
Palavra-chave:Multi-Agent Reinforcement Learning
Value-Alignment
Multi-Objective Reinforcement Learning
Descrição
Resumo:Proceedings of the 27th International Conference of the Catalan Association for Artificial Intelligence. The International Conference of the Catalan Association for Artificial Intelligence (CCIA) is a well-established annual event that brings together researchers in Artificial Intelligence from across the Catalan-speaking territories (southern France, Catalonia, Valencia, the Balearic Islands, and Alghero in Italy) as well as participants from around the world.