Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents.

Köster, Raphael; Hadfield-Menell, Dylan; Everett, Richard; Weidinger, Laura; Hadfield, Gillian K; Leibo, Joel Z

Köster, Raphael; Hadfield-Menell, Dylan; Everett, Richard; Weidinger, Laura; Hadfield, Gillian K; Leibo, Joel Z.

Afiliação

Köster R; DeepMind, London EC4A 3TW, United Kingdom; rkoster@deepmind.com jzl@deepmind.com.
Hadfield-Menell D; Computer Science and Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139.
Everett R; Center for Human-Compatible AI, University of California, Berkeley, CA 94720.
Weidinger L; DeepMind, London EC4A 3TW, United Kingdom.
Hadfield GK; DeepMind, London EC4A 3TW, United Kingdom.
Leibo JZ; Center for Human-Compatible AI, University of California, Berkeley, CA 94720.

Proc Natl Acad Sci U S A ; 119(3)2022 01 18.

Article em En | MEDLINE | ID: mdl-35022231

Assuntos

Aprendizagem; Reforço Psicológico; Normas Sociais; Meio Ambiente; Humanos

Palavras-chave

cultural evolution; multiagent reinforcement learning; norms; social norms; third-party punishment

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Reforço Psicológico / Normas Sociais / Aprendizagem Limite: Humans Idioma: En Ano de publicação: 2022 Tipo de documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google