Controlling the observation matrix to satisfy a structural matching condition reduces the belief-space HJB equation to a linear PDE with Feynman-Kac representation.
A generalized path integral control approach to reinforcement learning,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Path integral control is extended to Gaussian belief space for partially observed systems, yielding necessary and sufficient matching conditions, an exact Cole-Hopf linearization via Feynman-Kac, and the MPPI-Belief algorithm that outperforms certainty-equivalent and particle-filter baselines on a导航
Spectral kernel dynamics on fixed-topology surface graphs require distinction dynamics to restore conservation, and retaining at least beta_0 + beta_1 modes under a spectral-ordering assumption preserves all Betti numbers.
citing papers explorer
-
Path Integral Control for Partially Observed Systems with Controlled Sensing
Controlling the observation matrix to satisfy a structural matching condition reduces the belief-space HJB equation to a linear PDE with Feynman-Kac representation.
-
Path Integral Control in Gaussian Belief Space for Partially Observed Systems
Path integral control is extended to Gaussian belief space for partially observed systems, yielding necessary and sufficient matching conditions, an exact Cole-Hopf linearization via Feynman-Kac, and the MPPI-Belief algorithm that outperforms certainty-equivalent and particle-filter baselines on a导航
-
Spectral Kernel Dynamics for Planetary Surface Graphs: Distinction Dynamics and Topological Conservation
Spectral kernel dynamics on fixed-topology surface graphs require distinction dynamics to restore conservation, and retaining at least beta_0 + beta_1 modes under a spectral-ordering assumption preserves all Betti numbers.