Deep Reinforcement Learning with Double Q-Learning
Articolo
Articolo
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whet...
Idioma Inglés
Texto completo disponibleTexto completo detectado por patrón de enlace o metadatos.
Texto completo