Vincent Liu

Vincent Liu

PhD Candidate

University of Alberta

Biography

I am a PhD candidate at the RLAI Lab at the University of Alberta, working with Professor Martha White. I am interested in sequential decision making for real world problems. Specifically, my research focuses on offline reinforcement learning and off-policy learning.

Interests
  • Reinforcement Learning
  • Bandit Algorithms
  • In-context Learning
Education

  • PhD in Statistical Machine Learning, 2023

    University of Alberta

  • MSc in Statistical Machine Learning, 2019

    University of Alberta

  • BBA in Operations and Decision Management, 2017

    National Taiwan University

Publications

Vincent Liu, Prabhat Nagarajan, Andrew Patterson, Martha White (2023). When is Offline Policy Selection Feasible for Reinforcement Learning?. Under submission.

PDF

Vincent Liu, James R Wright, Martha White (2023). Exploiting action impact regularity and exogenous state variables for offline reinforcement learning. Journal of Artificial Intelligence Research.

Cite PDF

Vincent Liu, Yash Chandak, Philip Thomas, Martha White (2023). Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments. International Conference on Artificial Intelligence and Statistics.

Cite PDF Code

Vincent Liu, Han Wang, Ruo Yu Tao, Khurram Javed, Adam White, Martha White (2023). Measuring and Mitigating Interference in Reinforcement Learning. Conference on Lifelong Learning Agents.

PDF

Han Wang, Erfan Miahi, Martha White, Marlos C Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White (2022). Investigating the properties of neural network representations in reinforcement learning. arXiv preprint arXiv:2203.15955.

PDF

Han Wang, Archit Sakhadeo, Adam M White, James M Bell, Vincent Liu, Xutong Zhao, Puer Liu, Tadashi Kozuno, Alona Fyshe, Martha White (2022). No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL. Transactions on Machine Learning Research.

Cite PDF

Somjit Nath, Vincent Liu, Alan Chan, Adam White, Martha White (2020). Training Recurrent Neural Networks Online by Learning Explicit State Variables. International Conference on Learning Representations.

Cite PDF Code

Vincent Liu, Raksha Kumaraswamy, Lei Le, Martha White (2019). The utility of sparse representations for control in reinforcement learning. AAAI Conference on Artificial Intelligence.

Cite PDF

Andrew Jacobsen, Vincent Liu, Roshan Shariff, Adam White, Martha White (2019). A Value Function Basis for Nexting and Multi-step Prediction. The Multi-disciplinary Conference on Reinforcement Learning and Decision Making.

Brendan Bennett, Wesley Chung, Muhammad Zaheer, Vincent Liu (2019). Incrementally Learning Functions of the Return. The Multi-disciplinary Conference on Reinforcement Learning and Decision Making.

PDF

See all publications

Teaching

Teaching Assistant