David Abel (@dabelcs) / X

David Abel

627 posts

David Abel

@dabelcs

Scientist @GoogleDeepMind and Fellow @EdinburghUni | RL, philosophy, agency, foundations, alignment | office hours: tinyurl.com/dabel-mtg

Edinburgh, Scotland

Joined January 2018

Pinned
David Abel
@dabelcs
Nov 4, 2025
Thrilled to share our new #NeurIPS2025 paper done at @GoogleDeepMind, Plasticity as the Mirror of Empowerment We prove every agent faces a trade-off between its capacity to adapt (plasticity) and its capacity to steer (empowerment) Paper: david-abel.github.io/plasticity.pdf 🧵🧵🧵👇
103K
David Abel
@dabelcs
Dec 15, 2019
Just wrapped #NeurIPS2019! Notes here: david-abel.github.io/notes/neurips_…
David Abel
@dabelcs
Jun 16, 2019
Notes from @icmlconf here: david-abel.github.io/notes/icml_201… #ICML2019
David Abel
@dabelcs
May 10, 2019
My first ICLR was a blast! Notes for @iclr2019 available here: david-abel.github.io/notes/iclr_201… #ICLR2019
David Abel
@dabelcs
Mar 16, 2022
📘 My PhD thesis, "A Theory of Abstraction in Reinforcement Learning", is now up on arXiv! 🎉 arxiv.org/abs/2203.00397 Eternally grateful to my fabulous advisor, @mlittmancs, for his guidance, and to @BrownCSDept! Check it out 🙂
David Abel
@dabelcs
Apr 30, 2020
I successfully defended my Ph.D! 🎓 A massive thank you to my wonderful advisor, @mlittmancs, to @BrownCSDept, @BrownBigAI, and to my family, friends, mentors, and collaborators for their time and support over the years!
David Abel
@dabelcs
Sep 28, 2020
Life update! I moved to London to join the wonderful folks @DeepMind as a Research Scientist -- very much looking forward to the next chapter 🙂
David Abel
@dabelcs
Oct 20, 2023
Student researcher applications for @GoogleDeepMind are open! More details on the program here: deepmind.com/student-resear… I might be able to serve as a host -- if you're interested in working together, feel free to reach out 🙂
Student Researcher Program
From deepmind.google
74K
David Abel
@dabelcs
Jul 10, 2019
RLDM is just lovely! It was great to see everyone and hear about all the wonderful RL work going on -- already looking forward to RLDM 2021. Notes from this round available here: david-abel.github.io/notes/rldm_201… #RLDM2019
David Abel
@dabelcs
Dec 6, 2023
Reinforcement learning often studies agents that solve a task, then stop learning. In contrast, continual RL focuses on agents that never stop learning. But what does "never stop learning" mean? 🤔 Excited to share our #NeurIPS2023 paper on this! david-abel.github.io/crl.pdf 🧵
35K
David Abel
@dabelcs
Dec 1, 2021
Honoured that this work has received an outstanding paper award at NeurIPS 2021! 🎉🎊 Grateful to work with such a fantastic team: @wwdabney, @aharutyu, @Mark_Ho_, @mlittmancs, Doina Precup, and Satinder Singh 🥳
David Abel
@dabelcs
Nov 16, 2021
Really excited to share our upcoming #NeurIPS2021 paper! "On the Expressivity of Markov Reward" arxiv.org/pdf/2111.00876… Joint with @wwdabney, @aharutyu, @Mark_Ho_, @mlittmancs, Doina Precup, and Satinder Singh. We ask: What can Markov reward express? (1/5; a quick 🧵--> )
David Abel
@dabelcs
Nov 16, 2021
Really excited to share our upcoming #NeurIPS2021 paper! "On the Expressivity of Markov Reward" arxiv.org/pdf/2111.00876… Joint with @wwdabney, @aharutyu, @Mark_Ho_, @mlittmancs, Doina Precup, and Satinder Singh. We ask: What can Markov reward express? (1/5; a quick 🧵--> )
David Abel
@dabelcs
Jun 17, 2021
New tradition: Every Thursday I'll share a brief summary of an idea from math, CS, or philosophy that I find fascinating -- I'll keep a running list here: david-abel.github.io/blog/posts/fun… First up: Reflective Equilibrium! 1/n
David Abel
@dabelcs
Aug 25, 2020
New blog post! david-abel.github.io/blog/posts/vps… We summarize our @Aistats2020 paper about optimality-preserving abstractions in finite MDPs. Joint post & paper with Nathan Umbanhowar, @khimya, Dilip Arumugam, Doina Precup, and @mlittmancs. Paper: david-abel.github.io/papers/aistats…