DreamerV3 uses world models and robustness techniques to solve over 150 tasks across domains with a single configuration, including Minecraft diamond collection from scratch.
time- resolved
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Double preconditioning (DoPr) improves downstream task performance in test-time feedback settings without consistent gains in validation loss.
Momentum SGD pays a provable tracking penalty under distribution shift — lag growing as (1−β)⁻¹ and tracking floors worse than vanilla SGD in drift-dominated regimes.
citing papers explorer
-
Mastering Diverse Domains through World Models
DreamerV3 uses world models and robustness techniques to solve over 150 tasks across domains with a single configuration, including Minecraft diamond collection from scratch.
-
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Double preconditioning (DoPr) improves downstream task performance in test-time feedback settings without consistent gains in validation loss.
-
On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
Momentum SGD pays a provable tracking penalty under distribution shift — lag growing as (1−β)⁻¹ and tracking floors worse than vanilla SGD in drift-dominated regimes.