Vincent Liu

Researcher, RBC Borealis

Joined

August 2019

Names

Vincent Liu (Preferred)

Emails

****@ualberta.ca (Confirmed)

****@rbc.com (Confirmed)

Personal Links

Homepage

Google Scholar

ORCID

Career & Education History

Researcher

RBC Borealis (borealisai.com)

2025 – Present

Postdoc

University of British Columbia (ubc.ca)

2024 – 2024

PhD student

University of Alberta (ualberta.ca)

2019 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Martha White

2019 – 2023

Expertise

offline reinforcement learning

2019 – Present

off-policy policy evaluation

2019 – Present

reinforcement learning

2017 – Present

Publications

Switching the Loss Reduces the Cost in Batch Reinforcement Learning
Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesvari
- ICML 2024 Poster
- Readers: Everyone
Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Vincent Liu, Yash Chandak, Philip S. Thomas, Martha White
- Published: 01 Jan 2023, Last Modified: 10 May 2023
- CoRR 2023
- Readers: Everyone
When is Offline Hyperparameter Selection Feasible for Reinforcement Learning?
Vincent Liu, Prabhat Nagarajan, Andrew Patterson, Martha White
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
Han Wang, Archit Sakhadeo, Adam M White, James M Bell, Vincent Liu, Xutong Zhao, Puer Liu, Tadashi Kozuno, Alona Fyshe, Martha White
- Accepted by TMLR
- Readers: Everyone
Investigating the Properties of Neural Network Representations in Reinforcement Learning
Han Wang, Erfan Miahi, Martha White, Marlos C. Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White
- Published: 01 Jan 2022, Last Modified: 10 May 2023
- CoRR 2022
- Readers: Everyone
Exploiting Action Impact Regularity and Partially Known Models for Offline Reinforcement Learning
Vincent Liu, James Wright, Martha White
- Published: 01 Jan 2021, Last Modified: 10 May 2023
- CoRR 2021
- Readers: Everyone
Measuring and mitigating interference in reinforcement learning
Vincent Liu, Adam M White, Hengshuai Yao, Martha White
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Training Recurrent Neural Networks Online by Learning Explicit State Variables
Somjit Nath, Vincent Liu, Alan Chan, Xin Li, Adam White, Martha White
- Published: 01 Jan 2020, Last Modified: 10 May 2023
- ICLR 2020
- Readers: Everyone
Incrementally Learning Functions of the Return
Brendan Bennett, Wesley Chung, Muhammad Zaheer, Vincent Liu
- 2019 (modified: 24 Apr 2023)
- CoRR 2019
- Readers: Everyone
The Utility of Sparse Representations for Control in Reinforcement Learning
Vincent Liu, Raksha Kumaraswamy, Lei Le, Martha White
- Published: 01 Jan 2019, Last Modified: 10 May 2023
- AAAI 2019
- Readers: Everyone

View all 11 publications

Co-Authors

View all 39 co-authors