cvar-sf-repro: reproduction package for "A CVaR Safety Floor for Offline Reinforcement Learning under Unobserved Confounding: Duality and a Finite-Sample Validity Regime"
Reproduction package for the WAIMLAp 2026 paper A CVaR Safety Floor for Offline Reinforcement Learning under Unobserved Confounding: Duality and a Finite-Sample Validity Regime. It ships the confounded medical benchmark and its offline-data generator, the agents (CVaR-TRPO with the Safety-Floor acceptance gate, a CQL-s...