Mastering diverse control tasks through world models

by | Apr 2, 2025 | Uncategorized | 0 comments

Author

Nature, Published online: 02 April 2025; doi:10.1038/s41586-025-08744-2

A 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.

Archive Posts

0 Comments

Submit a Comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.