Sign in

Tom Ringstrom

@noreward4u.bsky.social
1.7K followers 694 following 33 posts

Reward-Free Model-based Maximalist. High-dimensional Empowerment. Self-Preserving Autonomous Agents. Theories of intelligence grounded in compositional control.

PostsRepliesMedia
Reposted by Tom Ringstrom
Aran Nayebi @anayebi.bsky.social · 04/03/2026
1/ As AI agents become increasingly capable, what must *inevitably* emerge inside them? We prove selection theorems: strong task performance forces world models, belief-like memory and—under task mixtures—persistent variables resembling core primitives associated with emotion.
1185
Reposted by Tom Ringstrom
Hadi Vafaii @hadivafaii.bsky.social · 17/09/2025
What drives behavior in living organisms? And how can we design artificial agents that learn interactively? 📢 To address these, the Sensorimotor AI Journal Club is launching the "RL Debate Series"👇 w/ @elisennesh.bsky.social, @noreward4u.bsky.social, @tommasosalvatori.bsky.social 🧵[1/5] 🧠🤖🧠📈
23710
Tom Ringstrom @noreward4u.bsky.social · 28/03/2025
First time seeing a wild giraffe. Just chillin’ on the side of the road.
040
Tom Ringstrom @noreward4u.bsky.social · 24/03/2025
They say don’t meet your heroes, but I traveled to South Africa and met mine and it was worth it. Stoffel the Honey Badger became a major inspiration for my PhD thesis when my advisor showed our lab a BBC show on clever animals who can solve long horizon tasks, presumably for abstract reasons.
141
Reposted by Tom Ringstrom
Pete Wolfendale @deontologistics.bsky.social · 13/03/2025
I've been thinking recently about Bostrom's notion of instrumental convergence, and what would entail instrumental divergence. There's an obvious sense in which infinitely large time horizons and infinitely small relevant probabilities play a role in washing out potential differences.
151
Tom Ringstrom @noreward4u.bsky.social · 06/01/2025
Unfortunately for SlipFrosty, a theory of instrumental intelligence is inseparable from a theory of normative intelligence. Abolish the value function!
182
Tom Ringstrom @noreward4u.bsky.social · 31/12/2024
My favorite interview from the past year, of philosopher Pete Wolfendale. Recommended to anyone interested in AI, the relationship between value, aesthetics and ethics, or anyone who wants a reason to abandon "rationality as Bayes + Utility". www.youtube.com/watch?v=0xMc...
youtube.com
The Gradient Podcast - Pete Wolfendale: The Revenge of Reason
YouTube video by The Gradient
0112
Tom Ringstrom @noreward4u.bsky.social · 26/12/2024
IMO, A problem with RL is that, in sparse-reward problems, value functions don’t have a general decomposition over high-dimensional transition kernels so people are trying to learn neural-net approximations to difficult-to-generalize functions from a lot of experience. Fun ep.
040
Tom Ringstrom @noreward4u.bsky.social · 17/12/2024
1102
Reposted by Tom Ringstrom
Surya Ganguli @suryaganguli.bsky.social · 06/12/2024
Stellar new work lead by the inimitable James Whittington in Neuron that develops a new theory unifying episodic and working memory and explains diverse hippocampal and prefrontal data: www.cell.com/neuron/fullt... w/Will Dorrell, @behrenstimb.bsky.social Mohamedy El Gaby
cell.com
A tale of two algorithms: Structured slots explain prefrontal sequence memory and are unified with hippocampal cognitive maps
The algorithm of the prefrontal working memory system on sequence memory tasks is not well understood, whereas it is well understood for the hippocampal episodic memory system. This work shows a mathematical duality between working and episodic sequence memory. This leads to a computational understanding of sequence working memory—as structured activity slots. This theory algorithmically explains recurrent neural network (RNN) and prefrontal representations during sequence memory tasks.
211230
Reposted by Tom Ringstrom
Jorge Ramírez-Ruiz @jramirezruiz.bsky.social · 26/11/2024
Starter packs are making it easier to keep constructing niches, so I made this one for people broadly interested in intrinsic motivation, with some focus on RL, neuroscience and cognitive science. Haven’t found many people on Bluesky that I wanted to add here, so help me out! go.bsky.app/TPNrnpE
374
Reposted by Tom Ringstrom
Tom Ringstrom @noreward4u.bsky.social · 25/11/2024
I wish we could turn some of the starter-packs into a custom feed rather than following everyone.
6111
Tom Ringstrom @noreward4u.bsky.social · 17/11/2024
BSKY academics, lets get to know each other! Quote this & tell me: 1) a project you are working on & 2) an odd idea/theory you aren’t working on but keep thinking about 1. High-dim planning 2. What are the minimal requirements for two agents to recognize each other as acting on behalf of reasons.
010
Reposted by Tom Ringstrom
Maxim Raginsky @mraginsky.bsky.social · 15/11/2024
The concept of system state is fundamental in theories of control and computation. I wrote down a few thoughts on the history of this idea and its connections to rationalist and empiricist perspectives in philosophy.
realizable.substack.com
Seeming Like a State
What's Nerode-equivalent to the past is prologue.
45019
Tom Ringstrom @noreward4u.bsky.social · 13/11/2024
Coming over from twitter, please give me a follow! My thesis below is on the connection between compositional planning and intrinsic motivation for self-preserving agents 🙂 drive.google.com/file/d/1peG7...
1101