Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning

no code implementations • 23 Nov 2022 • Tingting Zhao, Ying Wang, Wei Sun, Yarui Chen, Gang Niub, Masashi Sugiyama

Meanwhile, we divide the whole learning task into learning with the large-scale representation models in an unsupervised manner and learning with the small-scale policy model in the RL manner. The small policy model facilitates policy learning, while not sacrificing generalization and expressiveness via the large representation model.

reinforcement-learning Reinforcement Learning (RL) +1

Exploiting Dynamic and Fine-grained Semantic Scope for Extreme Multi-label Text Classification

no code implementations • 24 May 2022 • YuAn Wang, Huiling Song, Peng Huo, Tao Xu, Jucheng Yang, Yarui Chen, Tingting Zhao

TReaderXML dynamically obtains teacher knowledge for each text by similar texts and hierarchical label information in training sets to release the ability of distinctly fine-grained label-oriented semantic scope.

Multi Label Text Classification Multi-Label Text Classification +1