# Constraints Penalized Q-learning for Safe Offline Reinforcement Learning

> Research article (Proceedings of the AAAI Conference on Artificial Intelligence, 2022) · cited 43× · AI/ML

**Wikidata**: [openalex:W3185083385](https://www.wikidata.org/wiki/openalex:W3185083385)  
**Source**: https://4ort.xyz/entity/constraints-penalized-q-learning-for-safe-offline-reinforcement-learning