# Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling

> Research article (arXiv (Cornell University), 2019) · cited 53× · AI/ML

**Wikidata**: [openalex:W2991522342](https://www.wikidata.org/wiki/openalex:W2991522342)  
**Source**: https://4ort.xyz/entity/towards-optimal-off-policy-evaluation-for-reinforcement-learning-with-marginalized-importance-sampling