My name is Qingfeng Lan, a PhD student at the University of Alberta, Canada. I’m interested in designing simple and efficient algorithms supported by sound theories and verified by rigorous experiments. In particular, my research focuses on continual reinforcement learning and representation learning. Please see my CV for more information.


I’d like to chat to people with different research/social/cultural/educational backgrounds, as windows to see the unknown world. Feel free to contact me if you want to share anything (ideas, experiences, etc.) with me.

  • Email: qlan3 [AT]
  • WeChat (微信): Lancelqf
  • Twitter: lancelan3


  • Qingfeng Lan, A. Rupam Mahmood, Shuicheng Yan, Zhongwen Xu. Learning to Optimize for Reinforcement Learning. arXiv preprint arXiv:2302.01470, 2023. [paper][code]

  • Qingfeng Lan, Yangchen Pan, Jun Luo, A. Rupam Mahmood. Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation. TMLR, 2023. [paper][code]

  • Qingfeng Lan, Samuele Tosatto, Homayoon Farrahi, A. Rupam Mahmood. Model-free Policy Learning with Reward Gradients. AISTATS, 2022. (Poster) [paper] [code]

  • Qingfeng Lan. Variational Quantum Soft Actor-Critic. arXiv preprint arXiv:2112.11921, 2021. [paper][code]

  • Qingfeng Lan, Luke Kumar, Martha White, Alona Fyshe. Predictive Representation Learning for Language Modeling. arXiv preprint arXiv:2105.14214, 2021. [paper]

  • Qingfeng Lan, Yangchen Pan, Alona Fyshe, Martha White. Maxmin Q-learning: Controlling the Estimation Bias of Q-learning. ICLR, 2020. (Poster) [paper] [code] [video]

  • Zichen Zhang, Qingfeng Lan, Lei Ding, Yue Wang, Negar Hassanpour, Russell Greiner. Reducing Selection Bias in Counterfactual Reasoning for Individual Treatment Effects Estimation. NeurIPS Workshop on Causal Machine Learning, 2019. (Poster Spotlight) [paper]

  • Zhou Yang, Qingfeng Lan, Jiafeng Guo, Yixing Fan, Xiaofei Zhu, Yanyan Lan and Yue Wang, Xueqi Cheng: A Deep Top-K Relevance Matching Model for Ad-hoc Retrieval. CCIR, 2018. (Best Paper Award Candidate). [paper] [code]

Open-Source Code

  • Optim4RL: a framework of learning to optimize for reinforcement learning.
  • Explorer: a reinforcement learning frame based on Pytorch for exploring new research ideas.
  • Gym Games: a gym compatible version of various games for reinforcement learning.
  • Quantum Explorer: a quantum reinforcement learning framework for exploring new ideas, based on PyTorch and PennyLane.


  • University of Alberta, Sep 2020-Present

  • University of Alberta, Sep 2018-Aug 2020

    • Master of Science (Thesis-based) in Computing Science
    • Supervisor: Alona Fyshe
  • University of Chinese Academy of Sciences, Sep 2014-July 2018

    • Bachelor of Engineering, major in Computer Science and Technology, minor in Physics
    • Supervisor: Yanyan Lan; Tutor: Guojie Li
  • St Edmund Hall, University of Oxford, Oct 2017-Mar 2018