Really excited to attend @ICMLconf 2024 in Vienna in two weeks. Members of UCL DARK are going to present eight papers, including three Oral presentations and one Spotlight. Very proud of everyone involved!

Going to be at #ICML2024 all week! Excited to chat about UED, Genie, Decision Theory, AI Safety, and Open-Endedness. Don’t hesitate to reach out! If anyone wants to chat with other people around the UED space, reply in this thread. All the cool UED people should meet :)

Congratulations to best reviewer awards

Happy to meet so many smart people during our poster section today. 🎉 Thanks for stopping by and for all the kind feedback! 🫶🏽 So looking forward to see you tomorrow for our MOEs paper! 🚀

Thanks to my labmate, Toni Liu, for kindly hanging my poster at #ICML2024. Unfortunately, I couldn't make it to Vienna. If you are interested in this work, please reach out directly and/or watch this video run-through of the main findings: youtube.com/watch?v=2YqN2h…

Happening tomorrow morning! #1500 on Thursday from 11:30 - 13:00 Come learn about some common problems in neurosymbolic learning!

Come check out our poster tomorrow morning! It will be in Hall C, #1101

DearVCs, CEOs, VPs & Governments: Many people, including some AI researchers, thought this video generation and other AI advances would be impossible. Some researchers and engineers persevered with optimism, thought hard, derived novel mathematical algorithms and tractable

A thought provoking piece highlighting important flaws with the current RL research paradigm! It's a very nice read, I highly recommend checking it out.

🎉 2x RLC papers and 1x RLC workshop paper! Delighted to share that we have had 3 papers accepted to the first Reinforcement Learning Conference RL_Conference. 1. Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras We propose a self-supervised auxiliary

on saturday afternoon, go chat with Ghada Sokar about the effectiveness of tokenization in deep RL. don't flatten, tokenize! poster: Hall 3 + Hall 2B #363, 3-5:30 paper: openreview.net/forum?id=8oCrl… x.com/pcastr/status/…

See you later this morning at poster #392!

SIGBOVIK 2025 is out A live thread of papers that make me lightly smile: 1/ UPPERCASE IS ALL YOU NEED

Are world models necessary to achieve human-level agents, or is there a model-free short-cut? Our new #ICML2025 paper tackles this question from first principles, and finds a surprising answer, agents _are_ world models… 🧵

I'm excited to chat at #RLDM2025 about our (with Samuel Garcin) recent project: PixelBrax, where we combine the Brax physics engine with JAX-based rendering to enable end-to-end GPU training from pixels. paper: arxiv.org/abs/2502.00021 code: github.com/trevormcinroe/… Thread 1/

Hello world! This is the RL & Agents Reading Group We organise regular meetings to discuss recent papers in Reinforcement Learning (RL), Multi-Agent RL and related areas (open-ended learning, LLM agents, robotics, etc). Meetings take place online and are open to everyone 😊