Metadata
Title
Victor-Alexandru Darvariu
Category
undergraduate
UUID
c36e8c1ed25a4d1799b994e728d4ca67
Source URL
https://ori.ox.ac.uk/people/victor-alexandru-darvariu
Parent URL
https://ori.ox.ac.uk/orientate-seminar
Crawl Time
2026-03-09T03:25:19+00:00
Rendered Raw Markdown

Victor-Alexandru Darvariu

Source: https://ori.ox.ac.uk/people/victor-alexandru-darvariu Parent: https://ori.ox.ac.uk/orientate-seminar

EMAIL: victord@robots.ox.ac.uk

Biography

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

### Tree search in DAG spacewith an arbitrary ordering of the initial edges with model-based reinforcement learning for causal discovery

Tree search in DAG spacewith an arbitrary ordering of the initial edges with model-based reinforcement learning for causal discovery

Altmetric score is

### A Graph Reinforcement Learning Framework for Neural Adaptive Large Neighbourhood Search

A Graph Reinforcement Learning Framework for Neural Adaptive Large Neighbourhood Search

Altmetric score is

Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies

Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies

Altmetric score is

Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies

Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies

Altmetric score is

### PRORL: Proactive Resource Orchestrator for Open RANs Using Deep Reinforcement Learning

PRORL: Proactive Resource Orchestrator for Open RANs Using Deep Reinforcement Learning

Altmetric score is

View all

News

[05 Mar 2026

Oxford Engineering students power Dark Blue varsity victories](https://eng.ox.ac.uk/news/oxford-engineering-students-power-dark-blue-varsity-victories)

[04 Mar 2026

Study reveals unexpected long-term decline in energy use in small off-grid solar home systems](https://eng.ox.ac.uk/news/study-reveals-unexpected-long-term-decline-in-energy-use-in-small-off-grid-solar-home-systems)

[02 Mar 2026

Engineering Alumnus Paul M. Hubel named the 2026 Edwin H. Land Medal Recipient](https://www.optica.org/get_involved/awards_and_honors/awards/award_winner_press_releases-2a8be47a26a5ec81e9523c90ea425bbc-156f3d3faaa7084e1bc156a90f05be89/2026_edwin_land_medal_winner/)

[27 Feb 2026

Reception at no. 11 Downing Street marks anniversary of Oxford-Cambridge Growth Corridor](https://eng.ox.ac.uk/news/reception-at-no-11-downing-street-marks-anniversary-of-oxford-cambridge-growth-corridor)