# Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies

> Research article (International Conference on Machine Learning, 2021) · cited 19× · AI/ML

**Wikidata**: [openalex:W3166557699](https://www.wikidata.org/wiki/openalex:W3166557699)  
**Source**: https://4ort.xyz/entity/accelerating-safe-reinforcement-learning-with-constraint-mismatched-baseline-policies