Preprints

Ma, T.†, Yang, X., & Szabo, Z. (2024+). To Switch or not to Switch? Balanced Policy Switching in Offline Reinforcement Learning. arXiv preprint arXiv:2407.01837. [paper (arXiv), paper (pdf), code]

Ma, T.*, Zhu, J.*, Cai, H., Qi, Z., Chen, Y., Shi, C., & Laber, E. B†. (2023+). Sequential Knockoffs for Variable Selection in Reinforcement Learning. arXiv preprint arXiv:2303.14281. (SEEK). [paper (arXiv)]

Conference Proceedings

Ma, T.*†, & Yang, X*. (2024). A Framework for Policy Evaluation Enhancement by Diffusion Models. Tiny Papers ICLR (Invite to present). [paper]

Journal Publications

* Equal contribution.

† Corresponding author.

Talks

Balanced Policy Switching in Reinforcement Learning 2025.05 Workshop @ Representing, calibrating & leveraging prediction uncertainty from statistics to machine learning, Isaac Newton Institute & University of Cambridge

Balanced Policy Switching in Reinforcement Learning 2025.04 Statistics Research Showcase, LSE

Careers in Data Science and AI 2024.02 The Alan Turing Institute & The Brilliant Club

Sequential Knockoffs for Variable Selection in Reinforcement Learning 2023.05 PhD Presentation Events, LSE

Sequential Knockoffs for Variable Selection in Reinforcement Learning 2023.04 Prof. Tengyao Wang's Reading Group, LSE

Sequential Knockoffs for Variable Selection in Reinforcement Learning 2023.03 Prof. Qiwei Yao's Reading Group, LSE

Sequential Knockoffs for Variable Selection in Reinforcement Learning 2023.02 RL+X Online Seminar

Reinforcement Learning with Representation Learning 2022.10 LSE PhD Reading Group

Nonstationarity in a Markov Decision Process 2022.06 RL+X Online Seminar

Sequential Knockoffs for Variable Selection in Reinforcement Learning 2022.06 Research Showcase (Poster Section), LSE