Particle methods with deep learning approximate partially observed stochastic control problems, with a convergence proof and tests on linear-quadratic, nonlinear mean-field, and financial examples.
Optimal control of McKean-Vlasov systems under partial observation and hidden Markov switching
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A tractable framework for optimal stealthy attacks in partially observed linear systems via innovation likelihood detection, with hierarchical optimization and separation principle yielding semi-explicit adaptive attacks.
A decomposition method reduces LQ conditional McKean-Vlasov control problems with random coefficients to two decoupled stochastic optimal control problems whose optimal controls sum to the original optimum.
citing papers explorer
-
Optimal Design of Stealthy Attacks in Partially Observed Linear Systems: A Likelihood-Based Approach
A tractable framework for optimal stealthy attacks in partially observed linear systems via innovation likelihood detection, with hierarchical optimization and separation principle yielding semi-explicit adaptive attacks.