avatar.jpg

Runze Liu

Master Student, Tsinghua University.

I am currently a second-year master student at Tsinghua Shenzhen International Graduate School, Tsinghua University, supervised by Prof. Xiu Li. I received my bachelor’s degree with honours from Shandong University in June 2023. I am now a research intern at Shanghai AI Laboratory, working with Dr. Chenjia Bai. Before that, I was a research intern at Institute for AI at Peking University, working with Prof. Yali Du and Prof. Yaodong Yang. My research interest lies in Reinforcement Learning from Human Feedback (RLHF), Large Language Models (LLMs), and Embodied AI.

News

May 02, 2024 Our paper PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation is accepted by ICML 2024.
Jan 16, 2024 Our paper SEABO: A Simple Search-Based Method for Offline Imitation Learning is accepted by ICLR 2024.
Jun 30, 2023 I guaduated from Shandong University! The email address runzeliu@mail.sdu.edu.cn is no longer used. My new email address is lrz23@mails.tsinghua.edu.cn.
Sep 15, 2022 Our paper Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning is accepted by NeurIPS 2022.

Selected publications

* denotes equal contribution, denotes corresponding authorship.
  1. PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
    Runze Liu  , Yali Du  , Fengshuo Bai  , Jiafei Lyu  , and Xiu Li
    In International Conference on Machine Learning (ICML), 2024
  2. Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning
    Runze Liu  , Fengshuo Bai  , Yali Du  , and Yaodong Yang
    In Advances in Neural Information Processing Systems (NeurIPS), 2022