1 code implementation • NeurIPS 2023 • Yefan Zhou, Tianyu Pang, Keqin Liu, Charles H. Martin, Michael W. Mahoney, Yaoqing Yang
In particular, the learning rate, which can be interpreted as a temperature-like parameter within the statistical mechanics of learning, plays a crucial role in neural network training.
no code implementations • 6 Jul 2023 • Keqin Liu, Chengzhong Zhang
In this paper, we consider a general observation model for restless multi-armed bandit problems.
no code implementations • 9 Aug 2021 • Keqin Liu, Richard Weber, Ting Wu, Chengzhong Zhang
Restless bandit problems with even finite state spaces are PSPACE-HARD in general.
no code implementations • 8 Dec 2011 • Keqin Liu, Haoran Chen, Weibing Deng, Ting Wu
The multi-armed bandit (MAB) problem is a widely studied model in the field of reinforcement learning.