# MABSearch: The Bandit Way of Learning the Learning Rate—A Harmony Between Reinforcement Learning and Gradient Descent

> Research article (National Academy Science Letters, 2023) · cited 13× · AI/ML

**Wikidata**: [openalex:W4379284636](https://www.wikidata.org/wiki/openalex:W4379284636)  
**Source**: https://4ort.xyz/entity/mabsearch-the-bandit-way-of-learning-the-learning-ratea-harmony-between-reinforcement-learning-and-gradient-descent