Tail-Influence Sampling for CVaR Policy Evaluation
Policies with similar mean returns can differ sharply in rare failures, yet estimating lower-tail conditional value-at-risk (CVaR) accurately can require many costly rollouts. When different conditional components of a stochastic workflow can be queried separately, we ask how to allocate a fixed evaluation budget to es...
P. Bourigault, Xiao-Tong Ji, Matthieu Zimmer et al.
· 0 citations