← Search

Ji Jiang

2 accepted papers

2024

Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets

ICLR 2024poster

Previous literature on policy diversity in reinforcement learning (RL) either focuses on the online setting or ignores the policy performance. In contrast, offline RL, which aims to learn high-quality policies from batched data, has yet to fully leverage the intrinsic diversity of the offline datase…

Cited by 9SourcePDFScholar
2023

Improving Retrieval-Based Dialogue System Via Syntax-Informed Attention

ICASSP 2023accepted

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency structures into neural models can promote a better understa…

Cited by 0SourceScholar