# Pessimistic Reward Models for Off-Policy Learning in Recommendation

> Research article (Fifteenth ACM Conference on Recommender Systems, 2021) · cited 35× · AI/ML

**Wikidata**: [openalex:W3201286590](https://www.wikidata.org/wiki/openalex:W3201286590)  
**Source**: https://4ort.xyz/entity/pessimistic-reward-models-for-off-policy-learning-in-recommendation