Author

Haitao Hu

Observed name: Hu, Haitao

Institutions: ByteDance (China), The Hong Kong University of Science and Technology (Guangzhou)

Observed institutions: ByteDance (China), The Hong Kong University of Science and Technology (Guangzhou)

OpenAlex ID: A5146406688

DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment

2026 · Sun, Henan, Li, Zehua, et al. · arXiv (Cornell University)

IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents

2026 · Wang, Senhao, Cai, Chenghao, et al. · arXiv (Cornell University)

Works count: 2

Citation count:

H-index:

I10-index: