Excited to present our work (poster) today under the Self-Improvement perspective at this ICLR workshop - come for the speakers, stay for the posters 👀

Our paper with Victor-Alexandru Darvariu and Steve Hailes "Tree search in DAG space with model-based reinforcement learning for causal discovery" is now out in Proceedings of the Royal Society A. royalsocietypublishing.org/doi/full/10.10…

If you are at #AISTATS2025 and you are interested in information theory&interpretability, you should attend Charlie's poster presentation on Sunday.

If you are attending #AISTATS2025, do not miss Charlie's presentation tomorrow.

📢 Announcing the 10th Mental Health Workshop at the Ubicomp/ISWC 2025 Conference at Espoo, Finland. (October 12th or 13th (TBD), 2025) 📝 We invite paper submissions that explore the role of ubiquitous computing in both clinical and general populations concerning mental health

Congratulations to Elizaveta Tennant (Karmannaya) for passing her PhD viva today with a thesis on “Moral Alignment of Agentic AI Systems”! Well done Liza! And thanks to the examiners Joel Z Leibo and John Shawe-Taylor for examining Liza’s dissertation.

Today our paper with James Rudd-Jones and Maria Perez-Ortiz 🌍 "Multi-Agent Reinforcement Learning Simulation for Environmental Policy Synthesis" will be presented at the #AAMAS2025 Conference in Detroit. Time: 2pm ET Room: Richard Link to the paper: arxiv.org/abs/2504.12777

The second call for applications to the CDT in Cyber-Physical Risk is now open. I am offering two projects in the area of AI and cybersecurity. I would be happy to chat about this opportunity if you are interested. ucl.ac.uk/security-crime… Closing date: 15 June 2025.

Legendary - especially the Apple one with a design echoing the elegance of Victorian engravings (and of course Newton under the apple tree).

8 days left to apply!

Join our 4-year PhD program in Naples, Italy! 🇮🇹 ✅ 5 fully funded positions (€19k + travel abroad) ⏰ Deadline: Aug 27, 2025 -> Apply: bit.ly/3Tiumic #PhD #Italy #ControlTheory #DynamicalSystems #ComplexSystems #FullyFunded

At RLDM this week to present our work on incorporating diverse prior knowledge in RL (sample efficiency, safety, interpretability,...) Poster #94 on Thursday Full paper here: arxiv.org/abs/2306.01158 #RLDM2025

Dream jobs and where to find them. linkedin.com/jobs/view/4252…

Congrats to Francesco De Lellis! Finalist for the 2025 IEEE-CSS Italy Best Young Author Journal Paper Award 🎉 Our work: "Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning" 👉 ieeexplore.ieee.org/document/10534… With Giovanni Russo,Mirco Musolesi,Mario di Bernardo

Today Charlie Westphal will present our paper "Feature Selection for Network Intrusion Detection" in the main Research Track of ACM KDD 2025 in Toronto. Link to the paper: dl.acm.org/doi/pdf/10.114… #KDD2025