Derives a recursive characterization of the robust policy gradient via Wasserstein dual reformulation of the Bellman recursion and proposes a robust actor-critic algorithm for distributionally robust finite-horizon MDPs.
First order Martingale model risk and semi-static hedging
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Derives a projected McKean-Vlasov SDE whose flow converges to the minimizer of entropic weak optimal transport in adapted Wasserstein space.
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.
citing papers explorer
-
Projected McKean--Vlasov Dynamics for Entropic Weak Optimal Transport
Derives a projected McKean-Vlasov SDE whose flow converges to the minimizer of entropic weak optimal transport in adapted Wasserstein space.