Derives an explicit Gâteaux policy-gradient formula for entropy-regularized continuous-time mean-field control using the value function and cylindrical representations, then builds a model-based actor-critic scheme with PDE well-posedness analysis.
Hamilton-Jacobi equations in the Wasserstein space.Methods Appl
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
The paper reviews GHGF for HJ equations and proves a minimizing-movement construction for generalized characteristics plus that GHGF semi-flow invariant measures attaining c[H] are exactly the projected Mather measures.
citing papers explorer
-
Policy Gradient for Continuous-Time Mean-Field Control
Derives an explicit Gâteaux policy-gradient formula for entropy-regularized continuous-time mean-field control using the value function and cylindrical representations, then builds a model-based actor-critic scheme with PDE well-posedness analysis.
-
Recent progress in generalized Hamiltonian gradient flow: Singularities
The paper reviews GHGF for HJ equations and proves a minimizing-movement construction for generalized characteristics plus that GHGF semi-flow invariant measures attaining c[H] are exactly the projected Mather measures.