# Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation

> Research article (Proceedings of the AAAI Conference on Artificial Intelligence, 2024) · cited 10× · AI/ML

**Wikidata**: [openalex:W4393156756](https://www.wikidata.org/wiki/openalex:W4393156756)  
**Source**: https://4ort.xyz/entity/balance-reward-and-safety-optimization-for-safe-reinforcement-learning-a-perspective-of-gradient-manipulation