Weiqin Chen
 |
Weiqin Chen Ph.D. CandidateDepartment of Electrical, Computer, and Systems Engineering School of Engineering Rensselaer Polytechnic Institute Office: Jonsson Engineering Center Address: 110 8th Street, Troy, New York, 12180 E-mail: chenw18 [at] rpi [dot] edu; weiqin.chen7 [at] gmail [dot] com |
About me
I am a final-year PhD Candidate at Rensselaer Polytechnic Institute under the supervision of Prof. Santiago Paternain.
My current research interests lie at Reinforcement Learning, Optimization, LLM Safety Alignment, LLM Reasoning, Foundation Models, Control.
I am actively looking for a postdoctoral position starting from January 2026. Please feel free to reach out!
Recent news
May - Aug. 2025: I am excited to share that I will be joining IBM T. J. Watson Research Center as a Research Intern.
Apr. 2025: One paper has been accepted by TMLR (Featured Certification).
Jan. 2025: One paper has been accepted by ICLR 2025.
Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree SearchDec. 2024: Two papers have been accepted by AAAI 2025 workshops at GenPlan (Spotlight) and AI+ORMS (Oral).
A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms
Random Policy Enables In-Context Reinforcement Learning within Trust HorizonsOct. 2024: One paper has been accepted by NeurIPS 2024 workshop at LanGame.
PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision MakingJun. 2024: One paper has been accepted by ICML 2024 workshop at AutoRL.
Apr. 2024: I am pleased to share that I have passed the Doctoral Candidacy Examination, under the supervision of Prof. Santiago Paternain, Prof. Tianyi Chen, Prof. Koushik Kar, and Dr. Dharmashankar Subramanian.
Apr. 2024: One paper has been accepted by L4DC 2024.
Generalized Constraint for Probabilistic Safe Reinforcement LearningMar. 2024: One paper has been accepted by IEEE Transactions on Automatic Control.
Probabilistic Constraint for Safety-Critical Reinforcement LearningDec. 2023: I am honored to receive the 2023 Belsky Award for Computational Sciences and Engineering.
Dec. 2023: One paper has been accepted by AAMAS 2024 (Oral).
Adaptive Primal-Dual Method for Safe Reinforcement LearningMay - Aug. 2023: I am excited to share that I will be joining IBM T. J. Watson Research Center as a Research Intern.
Jan. 2023: One paper has been accepted by CISS 2023 (Oral).
Policy Gradients for Probabilistic Constrained Reinforcement LearningNov. 2022: I am pleased to share that I have passed the Doctoral Qualifying Examination.
Sept. 2021: I joined Rensselaer Polytechnic Institute to pursue a Ph.D. degree of Electrical Engineering.