Victor-Alexandru Darvariu
@vadarvariu.bsky.social
61 followers 130 following 110 posts
postdoc @ oxford robotics institute. interested in reinforcement learning, graphs, robots, and combinatorial optimization. https://victor.darvariu.me
Posts Media Videos Starter Packs
vadarvariu.bsky.social
While exploring this lovely city I bumped into a mobile sculpture by Alexander Calder. I'm not sure whether it's the one on the cover of the classic CLRS Introduction to Algorithms textbook, but it must be a closely related cousin at least!
vadarvariu.bsky.social
My colleague Alex Schutz (alex-schutz.github.io) will be presenting the paper "A Finite-State Controller Based Offline Solver for Deterministic POMDPs" (arxiv.org/abs/2505.00596) on Friday 22nd at 11:30 in the Planning and Scheduling session, please consider joining us.
vadarvariu.bsky.social
I am at IJCAI this week, please come say hi if you are in Montreal. Very happy to chat to people interested in reinforcement learning, planning, and graph learning!
vadarvariu.bsky.social
Dan is truly an amazing person and I hope he will do well in office. The problems ahead are very thorny, and the threat of the far-right will linger on, but it's worth taking a moment to celebrate his victory.
vadarvariu.bsky.social
Not even the Romanian diaspora in Western Europe, who counterintuitively voted overwhelmingly in favour of the Eurosceptic candidate (?!), could turn the tide.
vadarvariu.bsky.social
The country rallied around Dan in a campaign that involved many Romanians sitting down with their relatives and friends, explaining the threats of far-right politics.
vadarvariu.bsky.social
It was a truly strange two weeks in between voting rounds, in which Dan's opponent could not have sabotaged his leading position more if he tried (ghosting debates, ad-hominem attacks, ...).
vadarvariu.bsky.social
He managed an incredible victory against his Eurosceptic, ultranationalist adversary, who earned 41% of the vote in the first round against Dan's 21%.
vadarvariu.bsky.social
Dan went on to study at École Normale Supérieure and then did a PhD at Paris 13, returning to Romania afterwards as a mathematician, and eventually got into politics.
vadarvariu.bsky.social
I'd heard he did olympiads in his youth but I was blown away by his accomplishments! Other 1988 gold medallists whose names you might recognise are Ngô Bào Châu and Terence Tao, both of whom went on to earn Fields medals.
vadarvariu.bsky.social
In an increasingly rare W for democracy: Romania's president-elect, Nicușor Dan, is an IMO gold medallist. He participated in 1987 and 1988, and got perfect scores both times! www.imo-official.org/participant_...
International Mathematical Olympiad
www.imo-official.org
vadarvariu.bsky.social
The method is broadly applicable to any DAG construction task. If you work on causal inference, reinforcement learning, or combinatorial optimization, we believe CD-UCT offers a promising new direction. 7/
vadarvariu.bsky.social
We conduct a comprehensive empirical evaluation on both synthetic and real-world datasets. Across the board, CD-UCT consistently outperforms the state-of-the-art model-free RL approach and greedy search baselines. 6/
vadarvariu.bsky.social
Our method applies broadly to causal Bayesian networks, handling both discrete and continuous random variables, which makes it suitable for a wide range of domains. 5/
vadarvariu.bsky.social
A key contribution is an efficient, formally proven algorithm for excluding edges that would introduce cycles, enabling deeper and more effective discrete search during DAG construction. 4/
vadarvariu.bsky.social
CD-UCT incrementally builds directed acyclic graphs (DAGs) through a targeted tree search, improving substantially over more standard model-free approaches such as RL-BIC. 3/
vadarvariu.bsky.social
Identifying causal structure is fundamental to many fields including strategic decision-making, biology, and economics. In this paper, we introduce CD-UCT, a model-based reinforcement learning method for causal discovery. 2/
vadarvariu.bsky.social
Our paper "Tree search in DAG space with model-based reinforcement learning for causal discovery" has just been published in Proceedings of the Royal Society A. Joint work with Steve Hailes and @mircomusolesi.bsky.social 🧵 1/
Screenshot of the paper title, authors, abstract and miscellaneous bibliographical information as it appears in the published journal PDF.
vadarvariu.bsky.social
Just done migrating over to greener pastures.
vadarvariu.bsky.social
Feels great to be recognised together with my colleagues after a pretty intense reviewing season! 🫡 https://x.com/LogConference/status/1862602407395697123
vadarvariu.bsky.social
Thread with an overview of the paper:

vadarvariu.bsky.social
New pre-print now on arXiv, Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective (https://arxiv.org/abs/2404.06492). Joint work with Steve Hailes and @mircomusolesi. 🧵 1/10
vadarvariu.bsky.social
Super happy to see this work published in TMLR (with the survey certificate). We had a great discussion and experience with the venue overall, can't recommend it enough in comparison with the usual ML conference lottery. https://x.com/TmlrPub/status/1829141995115155541