Risk-averse SOC and MDP can be solved by dynamic programming with nested risk functionals, and under a quantile-gap condition the Value-at-Risk sample complexity grows roughly linearly in 1/(1-β).
Probabilities and Potential
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Risk-averse formulations of Stochastic Optimal Control and Markov Decision Processes
Risk-averse SOC and MDP can be solved by dynamic programming with nested risk functionals, and under a quantile-gap condition the Value-at-Risk sample complexity grows roughly linearly in 1/(1-β).