Scholar
Zhengran Ji
Google Scholar ID: hAejFdUAAAAJ
Duke University
Citations & Impact
Citations
47
H-index
5
i10-index
2
Publications
8
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning, published in Transactions on Machine Learning Research (TMLR 2025).
- HUMAC: Enabling Multi-Robot Collaboration from Single-Human Guidance, presented at the International Conference on Robotics and Automation (ICRA 2025).
- GUIDE: A framework for real-time human-guided reinforcement learning that accelerates policy learning by integrating continuous human feedback into dense rewards, featured at Neural Information Processing Systems (NeurIPS 2024).
- CREW: A platform for Human-AI teaming research, introduced in Transactions on Machine Learning Research (TMLR 2024).
- MnEdgeNet -- A regression deep learning network for decomposing Mn valence states from EELS and XAS L2,3 edges, published in Scientific Report, 2023.
Research Experience
- Currently working on Human-guided Reinforcement Learning, Multi-Agent Reinforcement Learning, and RLHF.
Education
- Received BS in Mathematics and Computer Science from the University of California, Irvine (UCI), advised by Prof. Huolin Xin; now pursuing a PhD at Duke University, advised by Prof. Boyuan Chen.
Background
- Currently a first-year PhD student in Computer Science at Duke University. Research interests include reinforcement learning, multi-agent/robot systems, human-in-the-loop learning, and RLHF.
Miscellany
- Contact: Email / CV / Scholar / Twitter / Github
