GPPI-AS offers a mesh-free, closed-form policy iteration solver for HJB and mean field game forward and inverse problems, with Schwarz acceleration cutting iterations roughly in half.
Convexification for a Coefficient Inverse Problem of Mean Field Games
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The globally convergent convexification numerical method is constructed for a Coefficient Inverse Problem for the Mean Field Games System. A coefficient characterizing the global interaction term is recovered from the single measurement data. In particular, a new Carleman estimate for the Volterra integral operator is proven, and it stronger than the previously known one. Numerical results demonstrate accurate reconstructions from noisy data.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gaussian process policy iteration with additive Schwarz acceleration for forward and inverse HJB and mean field game problems
GPPI-AS offers a mesh-free, closed-form policy iteration solver for HJB and mean field game forward and inverse problems, with Schwarz acceleration cutting iterations roughly in half.