David Abel

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 🧵🧵🧵👇

Attending #ICML and interested in World Models? PERSIST models the world within an explicit 3D latent representation. Come by to discover the unique capabilities this unlocks! 📍 Poster 2715 • Thursday • 2:30pm #ICML2026 #WorldModels #GenerativeAI #3DGeneration

This week's #PaperILike is "General agents contain world models" (Richens et al., ICML 2025). Brought to my attn by @dabelcs 's beautiful philosophy-laden talk at ICAPS. The explicit construction of a transition model from a policy is cool (Alg 1). PDF: arxiv.org/abs/2506.01622

Model-free agents learn to maximise reward without modelling the environment. Right? In recent work, we challenge this narrative by proving that agents, trained on a sufficiently rich set of goals, encode a unique and accurate world model in their value functions. 1/

@no_reward_for_u @Dilip_Arumugam @AlisonGopnik We should all chat! RLC?

@Dilip_Arumugam @AlisonGopnik @dabelcs Uh yes...

Great talk from @AlisonGopnik connecting causal learning with empowerment-gain (linked below), fully agree. Also got to chat over lunch with her and found out we're on the same wavelength :)

We are starting a new, nonprofit alignment organization, ⊢ Sequent Research, bringing together researchers previously on UK AISI’s Alignment Team, Timaeus, and elsewhere to research how to align superintelligence. We are hiring! 🧵

Just published in @PNASNews, we resolve a 50-year-old riddle from Richard Feynman's handwritten notes, prove and generalize it, and run a large-scale human study to reveal near-optimal heuristics in sequential decision problems: doi.org/10.1073/pnas.2…

@GlenBerseth Congratulations Glen!!

I am delighted to share the wonderful news that I have been granted tenure! This milestone marks the completion of my time as an Assistant Professor, and I am profoundly grateful for the support, collaboration, and inspiration I have received from this incredible community.

"Imperfect World Models are Exploitable" World models can look accurate, but still rank policies incorrectly, saying policy A is better than policy B when the real environment says the reverse. This paper formalizes that failure as model exploitation and proves it is basically unavoidable for any nontrivial, nonequivalent world model on broad policy sets. It also connects this to reward hacking and derives a safe horizon showing how model error compounds with planning depth.

Reminder that the deadline for the Finding the Frame workshop @RL_Conference is coming up on May 22 AoE ⏰ We're excited to read your submissions reflecting on the philosophy, practice, and formalisms of reinforcement learning! 🔗 More details: sites.google.com/view/findingth…

@Dr_Atoosa @GoogleDeepMind Congrats Atoosa!

🌟 Big personal news: I’m joining @GoogleDeepMind full-time in London starting this week. I’ll be working on the implications of AGI for human life, science, and society; on what it means to live, connect, and discover in a world where cognitive agency is no longer uniquely ours. The way we answer these questions will define what it means to be human. I can’t think of a better place to do it.

@shimon8282 @whi_rl Congratulations Shimon! Exciting news, welcome to DeepMind 🙂

Major personal news: After 6 years, I am leaving Waymo to lead a new multi-agent learning team at DeepMind.

Finding the Frame will be back at @RL_Conference 2026 with a fantastic speaker lineup! We welcome submissions that reflect on the philosophy, practice, and formalisms of reinforcement learning. 📅Submission deadline: May 22, 2026 (AoE) More details: sites.google.com/view/findingth…

@itsNVA7 Congratulations Nishanth!!

Thrilled to share that on March 20th, I defended my Ph.D. with flying colours! 🎨🎓🧠 My thesis, "The permanent and transient framework for continual RL," had an amazing reception from my committee: Peter Dayan, Marc Bellemare, Paul Masset, and Doina Precup.

Excited to be at (my first) #ICLR2026 this week to present work with Tom Griffiths (@cocosci_lab) on efficient exploration for LLM agents 🧵

Standard RL assumes a stable world. The real world may not. ♾ Introducing the Continual RL Workshop @RL_Conference 2026, Montreal, Canada. 🤖 Agents should never stop learning! 🖼️ Site: sites.google.com/view/continual… 📄 Submit: sites.google.com/view/continual…

Really excited to present our recent work at #ICLR2026 this week! We discover highly coordinated joint behaviours and integrate them into the skill sets of MARL agents, accelerating the search for effective joint strategies in downstream tasks.🧵 Paper: raulsteleac.github.io/iaro

New preprint of a paper with Eunice Yiu to appear in Philosophical Transactions A, Special issue: World models, 2026. The theoretical link between empowerment in RL and Bayesian causal models with cool new data. arxiv.org/abs/2512.08230

We're thrilled to announce Finding the Frame is back for the third time @RL_Conference 2026!🎉 Call for papers coming soon 🚀

We have the keynote speakers for RLC2026 now: Thrilled to welcome @contactrika, @ravi_iitm, @SheilaMcIlraith, @marcgbellemare, and @danijarh! Details: rl-conference.cc/index.html The RL community is coming together this August in Montréal, Québec, Canada. Hope you make it!

The "decoupling of information and energy" is a major point of divergence between biological and artificial computers. Brains are efficient, modern AI isn't. And energy consumption is the biggest bottleneck in scaling AI (you can't hallucinate electrons into existence). To address this we need an "energy-aware theory of computation." And this new preprint is an attempt to address this. [1/11] 🧵