Vincent Liu
Vincent Liu

Postdoctoral Research and Teaching Fellow

The University of British Columbia

About Me

I am a postdoc at UBC. I completed my PhD and MSc in Computing Science at the RLAI Lab at the University of Alberta, advised by Professor Martha White. My primary research focus is on offline reinforcement learning. I am broadly interested in applying machine learning and reinforcement learning to solve real-world decision-making problems.

Interests
  • Reinforcement Learning
  • Machine Learning
  • Data Science
Education
  • PhD in Statistical Machine Learning

    University of Alberta

  • MSc in Statistical Machine Learning

    University of Alberta

  • Bachelor of Business Administration

    National Taiwan University

Recent Publications
(2024). Switching the Loss Reduces the Cost in Batch Reinforcement Learning. International Conference on Machine Learning.
(2024). Investigating the properties of neural network representations in reinforcement learning. Artificial Intelligence.
(2023). When is Offline Policy Selection Feasible for Reinforcement Learning?. Under submission.
(2023). Exploiting action impact regularity and exogenous state variables for offline reinforcement learning. Journal of Artificial Intelligence Research.
(2023). Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments. International Conference on Artificial Intelligence and Statistics.
(2023). Measuring and Mitigating Interference in Reinforcement Learning. Conference on Lifelong Learning Agents.
(2022). No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL. Transactions on Machine Learning Research.
(2020). Training Recurrent Neural Networks Online by Learning Explicit State Variables. International Conference on Learning Representations.
(2019). The utility of sparse representations for control in reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence.
(2019). A Value Function Basis for Nexting and Multi-step Prediction. The Multi-disciplinary Conference on Reinforcement Learning and Decision Making.
(2019). Incrementally Learning Functions of the Return. The Multi-disciplinary Conference on Reinforcement Learning and Decision Making.
(2019). Attribute-aware recommender system based on collaborative filtering: Survey and classification. Frontiers in big Data.
Teaching

Instructor, University of British Columbia

  • DSCI 574 Spatial and Temporal Models, Winter 2025
  • DSCI 573 Feature and Model Selection, Fall 2024
  • DSCI 551 Descriptive Statistics and Probability for Data Science, Fall 2024
  • DSCI 512 Algorithms and Data Structures, Fall 2024

Teaching Assistant, University of Alberta

  • CMPUT 655 Reinforcement Learning I, Fall 2022
  • CMPUT 298 Basic of Machine Learning, Winter 2020
  • CMPUT 175 Introduction to the Foundations of Computation II, Fall 2017 and Winter 2018