# Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP

> Research article (arXiv (Cornell University), 2020) · cited 15× · AI/ML

**Wikidata**: [openalex:W2995519751](https://www.wikidata.org/wiki/openalex:W2995519751)  
**Source**: https://4ort.xyz/entity/q-learning-with-ucb-exploration-is-sample-efficient-for-infinite-horizon-mdp