Yicheng Luo
Papers
1
Total Citations
2
H-Index
1
About
Yicheng Luo is a researcher advancing the frontiers of reinforcement learning, with a focus on building safe, data-efficient systems for real-world robotics. His work centers on model-based reinforcement learning, where he develops algorithms that learn from limited interactions by leveraging learned dynamics models. Luo’s key contribution lies in principled uncertainty handling—his research on safe trajectory sampling ensures that policies not only solve target tasks but also respect physical constraints, making them viable for deployment in unpredictable environments. His 2023 paper, "Safe Trajectory Sampling in Model-Based Reinforcement Learning," has already garnered attention, earning 2 citations as a foundational step toward reliable autonomous decision-making. By addressing the critical challenge of feasibility and safety in robotics, Luo is helping bridge the gap between theoretical RL and practical application. His work is particularly relevant for students and researchers interested in how machine learning can be made both powerful and responsible, offering a roadmap for integrating safety guarantees into data-efficient learning pipelines.
Research Focus
Key Achievements
Top Papers
- 1Safe Trajectory Sampling in Model-Based Reinforcement Learning2 citations · 2023