Mastering diverse control tasks through world models

https://doi.org/10.1038/s41586-025-08744-2

DreamerV3: one fixed configuration beats specialized methods on over 150 tasks; first algorithm to collect Minecraft diamonds from scratch without human data or curricula (first diamond near 30M environment steps, about 17 days of play).

Self-play planning with learned models (AlphaZero, MuZero, Dreamer)