GNWM maps environments to a discrete 2D grid with snapping to stabilize autoregressive planning and learns generalized dynamics from maximum-entropy random walks.
(2021).Self-Organizing Representation Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Global Neural World Model: Spatially Grounded Discrete Topologies for Action-Conditioned Planning
GNWM maps environments to a discrete 2D grid with snapping to stabilize autoregressive planning and learns generalized dynamics from maximum-entropy random walks.