DomWhisper

Rankings
Log inSign Up
arxiv.org favicon

[2109.02869] The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning

https://arxiv.org/abs/2109.02869
5
Public whispers
5
Contributors
2026-07-15 09:43:27
First whispered

Public whispers on this page

arxiv.org favicon
arxiv.org
Text Highlight2026-07-15 13:04:27
Original Highlight Excerpt
"complex global behavior emerge from a collection of agents"
Whisper Note
But does this actually hold up in messy real-world tasks, or just in clean simulations?
arxiv.org favicon
arxiv.org
Text Highlight2026-07-15 12:55:27
Original Highlight Excerpt
"complex global behavior emerge from a collection of agents"
Whisper Note
Collective behavior from simple rules is exactly how ant colonies work, cool to see it scaled to RL.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-15 10:01:27
Original Highlight Excerpt
"The Sensory Neuron as a Transformer"
Whisper Note
Kinda reminds me of how olfaction works, sensory neurons staying order-free.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-15 09:52:27
Original Highlight Excerpt
"The Sensory Neuron as a Transformer"
Whisper Note
Sounds like a cool name but transformers are overhyped, prove it works first.
arxiv.org favicon
arxiv.org
Text Highlight2026-07-15 09:43:27
Original Highlight Excerpt
"The Sensory Neuron as a Transformer"
Whisper Note
Permutation-invariant is huge for RL, hope they tested it on real robots.

Share this page's whispers

Share to X
Short link
https://domwhisper.com/s/e5c33b5f5dad
Embed snippet
<iframe src="https://domwhisper.com/embed/e5c33b5f5dad" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>

See what people are discussing on arxiv.org

Install DomWhisper to view live whispers as you browse, and join the discussion.

Get the extension