AWhat changed
Combined robustness-oriented model and learning changes to train across diverse observation, action and reward regimes with fixed hyperparameters, including a Minecraft diamond-collection demonstration.
Scientific scope
Combined robustness-oriented model and learning changes to train across diverse observation, action and reward regimes with fixed hyperparameters, including a Minecraft diamond-collection demonstration. The original 2023 version is pinned; later expanded Nature results are not backdated. Fixed configuration within evaluated domains is not universal tuning-free control. World-model learning still needs environment interactions.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The original 2023 version is pinned; later expanded Nature results are not backdated. Fixed configuration within evaluated domains is not universal tuning-free control. World-model learning still needs environment interactions.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Mastering Diverse Domains through World Models
- Hafner et al.: robust cross-domain Dreamer control — author/company project record
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction