# Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value At Risk

> Research article (IEEE Robotics and Automation Letters, 2022) · cited 17× · AI/ML

**Wikidata**: [openalex:W4285066191](https://www.wikidata.org/wiki/openalex:W4285066191)  
**Source**: https://4ort.xyz/entity/efficient-off-policy-safe-reinforcement-learning-using-trust-region-conditional-value-at-risk