α-Rank: Multi-Agent Evaluation by Evolution

We introduce α-Rank, a principled evolutionary dynamics methodology, for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical game-theoretic solution concept called Markov-Conley chains (MCCs). The approach leverages continuous-time and discrete...

Descripción completa

Detalles Bibliográficos
Autores principales: Omidshafiei, Shayegan, Papadimitriou, Christos, Piliouras, Georgios, Tuyls, Karl, Rowland, Mark, Lespiau, Jean-Baptiste, Czarnecki, Wojciech M., Lanctot, Marc, Perolat, Julien, Munos, Remi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2019
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6617105/
https://www.ncbi.nlm.nih.gov/pubmed/31289288
http://dx.doi.org/10.1038/s41598-019-45619-9

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6617105/
https://www.ncbi.nlm.nih.gov/pubmed/31289288
http://dx.doi.org/10.1038/s41598-019-45619-9

Ejemplares similares