Linsen Dong
Papers
2
Total Citations
4
H-Index
2
About
Linsen Dong is a researcher at the forefront of **model-based reinforcement learning (MBRL)** , a subfield of AI that enhances sample efficiency by learning and approximating system dynamics. His primary contribution is the creation of **Baconian**, a unified, open-source framework designed to standardize and accelerate MBRL research. As detailed in his foundational 2019 paper and its 2021 follow-up, Baconian provides a modular architecture that simplifies the implementation and benchmarking of MBRL algorithms, addressing a critical need in a field where reproducibility and comparison are often challenging. This work has been instrumental in advancing research for applications like robotics and autonomous driving, where efficient learning from limited data is paramount. While his papers have garnered initial citations, the true impact of Dong’s contribution lies in the practical utility of the Baconian library itself, which serves as a vital tool for other researchers seeking to build and test their own MBRL models. His work represents a significant step toward making complex reinforcement learning systems more accessible and reproducible for the broader AI community.
Research Focus
Key Achievements
Top Papers
- 1
- 2Baconian : a unified model-based reinforcement learning library2 citations · 2021