Profile avatar
dabelcs.bsky.social
Researcher @ Google DeepMind and Honorary Fellow @ U of Edinburgh. RL, philosophy, foundations, AI. https://david-abel.github.io
6 posts 2,200 followers 260 following
Regular Contributor
Posts 14 Comments 3

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… 🧵 arxiv.org/abs/2506.01622

submitted 3 days ago • 1 comment

New paper with Iason Gabriel on "Characterizing AI agents" is out! 2025 is being called the year of AI agents, with overwhelming headlines about them every day. But we lack a shared vocabulary to distinguish their fundamental properties. Our paper aims to bridge this gap. A 🧵

submitted 35 days ago • 2 comments

Barto and Sutton receive the Turing award! Amazing recognition for two kind, pioneering, and genuinely inspiring scientists. Congratulations!! awards.acm.org/about/2024-t...

submitted 94 days ago • 0 comments

new paper: "Evolution and the Knightian Blindspot of Machine Learning" Our ever-changing world bubbles with surprise and complexity. General AI must include handling unforeseen situations with grace. Yet this issue largely lies outside AI's formalisms: a blind spot. (1/n)

submitted 134 days ago • 2 comments

The RLDM workshop list is now up! Have a look: rldm.org/call-for-wor... More workshop details coming soon :) There were so many wonderful submissions---this was really tough for the committee. Huge thanks to all involved, and looking forward to seeing folks in Dublin

submitted 146 days ago • 2 comments

📢 Call for Abstracts 📢 Submit your extended abstracts on "learning and decision-making over time to achieve a goal" to #RLDM2025. Successful applications will be selected for poster or oral presentation to an interdisciplinary audience. 🗓️ Deadline: Jan 15th 🔗 Learn more: rldm.org/call-for-abs...

submitted 179 days ago • 0 comments

📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social! What you get, why you should be interested and more, all below in a short 🧵👇

submitted 179 days ago • 4 comments

I'm hiring PhD students at Brown CS! If you're interested in human-robot or AI interaction, human-centered reinforcement learning, and/or AI policy, please apply. Or get your students to apply :). Deadline Dec 15, link: cs.brown.edu/degrees/doct.... Research statement on my website, www.slbooth.com

submitted 181 days ago • 0 comments

Hey 👋 the deadline for submitting workshop proposals to #RLDM is fast approaching! We would especially love creative structures for workshops, like hackathons, debates or other traditional formats. Follow @rldmdublin2025.bsky.social for more updates!

submitted 186 days ago • 0 comments

We're looking for nominations for speakers to give a tutorial on RLDM topics to mixed audience of psychologist, neuroscientists and AI folks. Please contribute!

submitted 186 days ago • 0 comments

Are there limits to what you can learn in a closed system? Do we need human feedback in training? Is scale all we need? Should we play language games? What even is "recursive self-improvement"? Thoughts about this and more here: arxiv.org/abs/2411.16905

submitted 191 days ago • 7 comments

Have ideas for an interdisciplinary workshop? Get involved at RLDM to tackle key challenges, open problems, or controversial topics! 🎤 Formats: Talks, panels, hackathons, debates—your choice! 👥 All career stages welcome to lead. 🗓️ Deadline to apply: 10th December. Link 🔽 rldm.org/call-for-wor...

submitted 192 days ago • 1 comment

RLDM will be held next year in Dublin! A reminder that the call for workshops is out: rldm.org/call-for-wor... The workshops are one of my favourite parts of the conference :) please get in touch if you have any questions!

submitted 197 days ago • 1 comment

Come join us at Trinity College Dublin for the 6th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2025) Abstract deadline January 15: rldm.org/submit

submitted 204 days ago • 1 comment