Zhi-Quan Luo

A new framework simplifies reinforcement learning for complex environments.

Algorithms enhance player strategies in uncertain game environments.

This article explores optimization challenges in Transformers and the effectiveness of Adam over SGD.

This study examines how prior knowledge improves decision-making in reinforcement learning.

Adam-mini reduces memory usage for training large language models while maintaining performance.

A new method combines AI models to improve decision-making under uncertainty.

A new approach enhances language model responses and reduces overfitting.

A look at bi-level optimization methods and their impact on machine learning models.

Discover efficient algorithm performance under strict time limits.