Mastering diverse control tasks through world models

شارك رابطًا

2025-04-02 20:16:21 - ترجمة -

WWW.NATURE.COM

Nature, Published online: 02 April 2025; doi:10.1038/s41586-025-08744-2A general reinforcement-learning algorithm, called Dreamer, outperforms specialized expert algorithms across diverse tasks by learning a model of the environment and improving its behaviour by imagining future scenarios.

0 التعليقات 0 المشاركات 266 مشاهدة 0 معاينة