Contextual PPC uses world-model score densities to impose Riemannian structure on actions, yielding a safety bound on manifold distance controlled by estimation error and barrier curvature that improves with richer context.
Maximum entropy reinforcement learning via energy-based normalizing flow,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Safety-Critical Contextual Control via Online Riemannian Optimization with World Models
Contextual PPC uses world-model score densities to impose Riemannian structure on actions, yielding a safety bound on manifold distance controlled by estimation error and barrier curvature that improves with richer context.