Pihe Hu
 |
PhD Student |
About me
I am a PhD student in Computer Science under the supervision of Prof. Longbo Huang at Tsinghua University (THU). I received the B.S. degree in Computer Science and Technology from Shanghai Jiao Tong University (SJTU), China, in 2019.
Research
My research interests include
Model Acceleration
Reinforcement Learning Theory
Deep Reinforcement Learning
Network Optimization
Recent Publications
Pihe Hu*, Yu Chen*, Longbo Huang. “Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs.” International Conference on Learning Representations (ICLR), 2023 [OpenReview] (* indicates joint first author)
Yiqin Tan*, Pihe Hu*, Ling Pan, Longbo Huang. “RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch.” International Conference on Learning Representations (ICLR), 2023 [OpenReview] (Spotlight) (* indicates joint first author)
Pihe Hu, Ling Pan, Yu Chen, Zhixuan Fang, Longbo Huang. “Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning.” International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc), 2022. [pdf]
Pihe Hu, Yu Chen, Longbo Huang. “Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation.” International Conference on Machine Learning (ICML), pp. 8971-9019. PMLR, 2022. [pdf] (Erratum: an issue in building the over-optimistic value function is addressed by the ‘‘rare-switching’’ mechanism in [He et al. 2022.], and the fixed version is given in [arxiv])