Hi, my name is Linh. I'm a postdoctoral researcher at UofT, advised by Prof. Scott Sanner. Before joining UofT, I received my PhD in Computer Science from A2I2, Deakin University, my BSc. Hons in Information Technology from the University of Engineering and Technology, Vietnam National University, Hanoi.
My research interests center on Machine Learning, with a current focus on Reinforcement Learning and World Models. I am particularly interested in exploring how to effectively learn world models from high-dimensional data and leverage them for decision-making in complex environments. My work aims to contribute to the development of more efficient and robust algorithms for decision-making in real-world scenarios, where uncertainty and complexity are prevalent.
I'm always open to discussions and collaborations. Please feel free to reach out via email if you have a potential opportunity in mind, are interested in collaborating, or would just like to chat about research.
Outside of research, I enjoy coding and building things. In my spare time, I love reading books, listening to music, taking photos, running (both road and trails marathon), cycling, and hiking. I'm also learning to play (classic) guitar.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "News
Selected Publications (view all )
DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning
Linh Le, Minh Hoang Nguyen, Duc Kieu, Hung Le, Hung The Tran, Sunil Gupta
European Conference on Artificial Intelligence (ECAI) 2025
We study cross-domain offline RL with limited target data, where neural domain-gap estimators often overfit and only part of the source dataset overlaps with the target domain. We propose DmC, combining a k-NN proximity estimator with a nearest-neighbor–guided diffusion model to generate target-aligned source samples, and show strong gains over prior methods on MuJoCo benchmarks.
DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning
Linh Le, Minh Hoang Nguyen, Duc Kieu, Hung Le, Hung The Tran, Sunil Gupta
We study cross-domain offline RL with limited target data, where neural domain-gap estimators often overfit and only part of the source dataset overlaps with the target domain. We propose DmC, combining a k-NN proximity estimator with a nearest-neighbor–guided diffusion model to generate target-aligned source samples, and show strong gains over prior methods on MuJoCo benchmarks.
Policy Learning for Off-Dynamics RL with Deficient Support
Linh Le, Hung The Tran, Sunil Gupta
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2024
We tackle cross-domain policy transfer under large dynamics mismatch, where the common "full support" assumption (the simulator covers all target transitions) is unrealistic. We propose a simple method that skews and extends source support toward target support to reduce support deficiencies, and show consistent gains over prior approaches across diverse benchmarks.
Policy Learning for Off-Dynamics RL with Deficient Support
Linh Le, Hung The Tran, Sunil Gupta
We tackle cross-domain policy transfer under large dynamics mismatch, where the common "full support" assumption (the simulator covers all target transitions) is unrealistic. We propose a simple method that skews and extends source support toward target support to reduce support deficiencies, and show consistent gains over prior approaches across diverse benchmarks.
All publications
Experience
-
Sep. 2020 - Jul. 2022VNU University of Engineering and Technology
Teaching assistant for the Computer science courses: Introduction to Informatics, Advanced Programming, Data Structures and Algorithms, Image Processing. -
Sep. 2020 - Jul. 2022UET AILab, Vietnam National University
Research about Medical Image Translation.
Education
-
Aug. 2022 - Feb. 2026A2I2, Deakin University
Deakin Applied Artificial Intelligence Initiative
Ph.D. Candidate -
Sep. 2016 - Jul. 2020University of Engineering and Technology, Vietnam National University, Hanoi
B.S. in Computer Science (Honor Program)
🏆 Honors & Awards
-
Deakin University Postgraduate Research Scholarship for PhD candidature.2022
-
Certificate of merit awarded by the VNU University of Engineering and Technology for Outstanding student of the entire course.2020
-
1st Place in Digital Race FPT (Autonomous car competition) 2019, round UET.2019
Misc
Services
Reviews: TMLR (2025, 2026), RLC (2025, 2026), ECML(2025), ACML(2025), EWRL (2025).