Scholar
Victor-Alexandru Darvariu
Google Scholar ID: eRiLIWgAAAAJ
Oxford Robotics Institute, University of Oxford
Citations & Impact
Citations
186
H-index
9
i10-index
8
Publications
20
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- Published a paper titled 'Tree search in DAG space with model-based reinforcement learning for causal discovery' in Proceedings of the Royal Society A. Proposed the CD-UCT algorithm and made the code and benchmarks publicly available. Additionally, shared two new pre-prints: one proposing the GNARL method, which reimagines Neural Algorithmic Reasoning as Markov Decision Processes; and another, in collaboration with researchers at Imperial College, leveraging Graph RL to accelerate a fundamental discovery task in atomic physics.
Research Experience
- Works as a Postdoctoral Researcher at the Oxford Robotics Institute, University of Oxford, participating in the GOALS team's research. Also serves as a Retained Lecturer in Engineering Science at Jesus College and an Honorary Research Fellow at UCL Computer Science.
Education
- Information not provided
Background
- A computer scientist working as a Postdoctoral Researcher at the Oxford Robotics Institute, University of Oxford, where he is part of the GOALS group led by Nick Hawes. He is also a Retained Lecturer in Engineering Science at Jesus College and an Honorary Research Fellow at UCL Computer Science. His interests lie in reinforcement learning (RL) and artificial intelligence (AI) more broadly. The key insight behind his work is the ability of RL to discover, by trial-and-error, ways of solving decision-making problems that can outperform or complement traditional methods. His work develops rigorous RL methodologies, especially for graph-structured systems (Graph RL), and applies them to scientific disciplines as diverse as robotics, operations research, and statistics.
Miscellany
- On the job market for Lecturer or Assistant Professor positions starting in 2026/27.
