A model-free off-policy actor-critic algorithm is constructed for dynamic expectile and CVaR using a surrogate policy gradient without transition perturbation and elicitability-based value learning, with empirical outperformance in risk-averse domains.
Mathematical programming , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Distributionally robust games are defined via coherent risk measures, with proofs of equilibrium existence for ambiguity sets, utility loss bounds, PPAD-completeness results, multilinear complementarity formulations, and numerical validation of out-of-sample performance.
citing papers explorer
-
Actor-Critic Algorithm for Dynamic Expectile and CVaR
A model-free off-policy actor-critic algorithm is constructed for dynamic expectile and CVaR using a surrogate policy gradient without transition perturbation and elicitability-based value learning, with empirical outperformance in risk-averse domains.
-
Distributionally Robust Games via Coherent Risk Measures
Distributionally robust games are defined via coherent risk measures, with proofs of equilibrium existence for ambiguity sets, utility loss bounds, PPAD-completeness results, multilinear complementarity formulations, and numerical validation of out-of-sample performance.