# Instance-Dependent ℓ<sub>∞</sub>-Bounds for Policy Evaluation in Tabular Reinforcement Learning

> Research article (IEEE Transactions on Information Theory, 2020) · cited 24× · AI/ML

**Wikidata**: [openalex:W3090442079](https://www.wikidata.org/wiki/openalex:W3090442079)  
**Source**: https://4ort.xyz/entity/instance-dependent-l-sub-sub-bounds-for-policy-evaluation-in-tabular-reinforcement-learning