About me

I’m a first year Ph.D. student at CSE, the Hong Kong University of Science and Technology, supervised by Prof. Tong Zhang. I received my master’s and bachelor’s degrees from the Department of Automation at Tsinghua University. I am furtunate to have been working closely with Prof. Chongjie Zhang (IIIS, Tsinghua University), Dr. Lei Han (Tencent), and Prof. Meng Fang (University of Liverpool). My research interests lie in deep reinforcement learning (RL), especially goal-conditioned RL, offline RL and model-based RL, and the application of RL algorithms to game AI and robotics.

Currently, I am actively researching ways to improve the robustness and generalization abilities of deep reinforcement learning. Feel free to contact me by email if you are interested in discussing or collaborating with me.

Publications

Conference Papers

• What Is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL? Rui Yang, Yong Lin, Xiaoteng Ma, Hao Hu, Chongjie Zhang, Tong Zhang. International Conference on Machine Learning (ICML) 2023. (coming soon)

• RORL: Robust Offline Reinforcement Learning via Conservative Smoothing. Rui Yang $^*$, Chenjia Bai $^*$, Xiaoteng Ma, Zhaoran Wang, Chongjie Zhang, Lei Han. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022.PDF

• Exploiting Reward Shifting in Value-Based Deep RL. Hao Sun, Lei Han, Rui Yang, Xiaoteng Ma, Jian Guo, Bolei Zhou. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022.

• Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL. Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang, Yali Du, Xiu Li, Lei Han, Chongjie Zhang. International Conference on Learning Representations (ICLR), 2022. PDF

• FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization. Lanqing Li, Rui Yang, Dijun Luo. International Conference on Learning Representations (ICLR), 2021.

• MHER: Model-based Hindsight Experience Replay. Rui Yang, Meng Fang, Lei Han, Yali Du, Feng Luo, Xiu Li. NeurIPS 2021 Workshop DeepRL.

• Combining Hindsight with Goal-enhanced Prediction for Multi-goal Reinforcement Learning. Rui Yang, Feng Luo, Xiu Li. IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI) 2021.

Journal Papers

• Efficient Multi-Goal Reinforcement Learning via Value Consistency Prioritization. Jiawei Xu $^*$, Shuxing Li $^*$, Rui Yang, Chun Yuan, Lei Han. Journal of Artificial Intelligence Research (JAIR), 2023.

• A survey on sparse reward algorithms in reinforcement learning-theory and experiment. Rui Yang, Jiangpeng Yan, Xiu Li. CAAI Transactions on Intelligent Systems (in Chinese), 2020

Educations

• 2022.09 - now, Ph.D. student, Department of Computer Science and Engineering, the Hong Kong University of Science and Technology.
• 2019.09 - 2022.07, Master, Department of Automation, Tsinghua University.
• 2015.09 - 2019.07, Bachelor, Department of Automation, Tsinghua University.

Experiences

• Tencent AI Lab (Jun. 2020 – Sep. 2020)

  Researched on multi-step HER and offline meta RL.

• Meituan Financial Service Group (Jul. 2019 – Sep. 2019)

  Controlled the advertising speed of Meituan app via a pacing PI control algorithm.

Services

Conference Reviewer: ICML (2022), NeurIPS (2022,2023)

Others

During my leisure time, I like sports such as running, table tennis and swimming. I used to be an amateur long-distance runner. I finished a half marathon (21.0975 km) in 1h30min and a marathon (42.195 km) in 3h36min.