Dr
Victor-Alexandru
Darvariu

School of Electrical and Electronic Engineering

Lecturer in Machine Learning for Engineering

Image of Dr Victor Alexandru Darvariu
Dr Victor Alexandru Darvariu
Profile picture of Image of Dr Victor Alexandru Darvariu
v.darvariu@sheffield.ac.uk

Full contact details

Dr Victor-Alexandru Darvariu
School of Electrical and Electronic Engineering
Amy Johnson Building
Portobello Street

Sheffield

S1 3JD

Profile

I am currently a Lecturer in Machine Learning for Engineering in the School of Electrical and Electronic Engineering at the University of Sheffield. Before joining the School in November 2026, I was a Postdoctoral Research Assistant at the Oxford Robotics Institute, University of Oxford from August 2024. My prior appointment was as a Research Fellow in Machine Learning at the Department of Computer Science, University College London (UCL). My PhD in Computer Science, awarded in May 2023 by UCL, was part of the doctoral programme of The Alan Turing Institute and included a research internship at Spotify. I hold an MSci in Computer Science from the University of Birmingham (2013-2018), which included a year spent as a software engineer in the financial services sector with Morgan Stanley.

My research focuses on artificial intelligence (AI), particularly graph reinforcement learning – the intersection of reinforcement learning, planning, and machine learning on graphs. The central insight behind my work is the potential of reinforcement learning to discover novel and effective strategies for solving complex decision-making and optimisation problems, especially those that can be formulated over graphs (networks). I am motivated by the promise of AI to accelerate discovery and address important challenges in science and engineering through interdisciplinary collaborations with domain experts.  The applications of my work span diverse disciplines including robotics, operations research, and the physical sciences.

Research interests
  • Graph reinforcement learning, neural combinatorial optimisation, and neural algorithmic reasoning
  • Reinforcement learning and planning for sequential decision-making, including multi-agent approaches
  • Graph representation learning and graph neural networks
  • Autonomous systems and robotics, particularly long-term autonomy and environmental monitoring
  • AI for scientific and engineering applications, including causal discovery, the physical sciences, sustainable energy, and computing systems
Publications

There has been a problem showing this information. Please try again later.