Victor is a Postdoctoral Research Assistant at the Oxford Robotics Institute. His primary project investigates mission planning techniques for underwater glider robots in collaboration with the National Oceanography Centre.
His primary goal is the development of artificial intelligence techniques for solving challenging decision-making problems effectively. His research interests span reinforcement learning and planning, combinatorial optimization, network science, graph neural networks, game theory, and multi-agent systems. He also investigates applications of such techniques in areas as diverse as robotics, operations research, computer systems, and causal inference.
Victor was previously a Postdoctoral Research Fellow in Machine Learning in the Autonomous Systems group at the Department of Computer Science, University College London (UCL). His PhD in Computer Science, awarded in May 2023 from UCL, was sponsored by The Alan Turing Institute through its doctoral programme and included a research internship at Spotify. Prior to this, he attended University of Birmingham between 2013 and 2018, obtaining an MSci in Computer Science with an Industrial Year. During this time, he worked as a software engineer in the financial services industry.
To find out more, visit https://victor.darvariu.me.
Most Recent Publications
Deeper Structure of Marine Heatwaves: Glider-Detected Anomalies in the North Sea
Deeper Structure of Marine Heatwaves: Glider-Detected Anomalies in the North Sea
Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
Online Navigation Planning for Long-term Autonomous Operation of Underwater Gliders
Online Navigation Planning for Long-term Autonomous Operation of Underwater Gliders
Gaussian Process Aggregation for Root-Parallel Monte Carlo Tree Search with Continuous Actions
Gaussian Process Aggregation for Root-Parallel Monte Carlo Tree Search with Continuous Actions
Accelerating Atomic Fine Structure Determination with Graph Reinforcement Learning
Accelerating Atomic Fine Structure Determination with Graph Reinforcement Learning
