Noticias

¡RECUERDA QUE SI ERES UN NUEVO USUARIO, DEBES PRESENTARTE PARA PODER PUBLICAR MENSAJES! | TENEMOS CANAL OFICIAL DE TELEGRAM: t.me/unity3dspain

Solving sparse-reward tasks with Curiosity

Iniciado por pioj, Junio 26, 2018, 02:05:37 PM

Tema anterior - Siguiente tema
We just released the new version of ML-Agents (v0.4), and one of the new features we are excited to share with everyone is the ability to train agents with an additional curiosity-based intrinsic reward. Since there is a lot to unpack in this feature, I wanted to write an additional blog post on it. In [...]
Ver artículo completo...

Etiquetas: