iiinova — where your digital self keeps evolving

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 20/11/2025

But why did you almost cry? Which type of tears

110

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 26/08/2025

Actually you reminded me to just now post it on bluesky 😄 ty

020

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 26/08/2025

E71: Jake Beck, Alex Goldie, & Cornelius Braun on Sutton's OaK, Metalearning, LLMs, Squirrels at @rl-conference.bsky.social A few thoughts with @jakeabeck.bsky.social, @alexgoldie.bsky.social and @corneliusbraun.bsky.social after Rich Sutton's fascinating lecture on his OaK architecture at UofA

130

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 26/08/2025

E69: Thomas Akam on Model-based RL in the Brain @ox.ac.uk neuroscientist Prof Akam on RL in brains vs machines, dopamine as TD-error (or not), hippocampal replay & Dyna, model-free vs model-based myths, and why ML experts should consider neuroscience careers.

220

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 26/08/2025

His textbook: Multi-Agent Reinforcement Learning: Foundations and Modern Approaches Stefano V. Albrecht, Filippos Christianos, Lukas Schäfer Published by MIT Press, 2024 marl-book.com

marl-book.com

Multi-Agent Reinforcement Learning: Foundations and Modern Approaches

Textbook published by MIT Press (2024)

110

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 26/08/2025

E67: Stefano Albrecht on Multi-Agent RL @ RLDM 2025 Stefano Albrecht shares the story behind his multi-agent RL textbook, and how DeepFlow AI turns these ideas into action with LLM-powered agents for business automation. Recorded at @rldmdublin2025.bsky.social

120

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 25/06/2025

Tagging our guest: @satindersingh.bsky.social Mentioned in this interview: @yaelniv.bsky.social, Rich Sutton, Peter Dayan

020

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 25/06/2025

E66: Satinder Singh: The Origin Story of RLDM @ RLDM 2025 Professor Satinder Singh of Google DeepMind and U of Michigan is co-founder of ‪@rldmdublin2025.bsky.social‬ Here he narrates the origin story of the Reinforcement Learning and Decision Making meeting (not conference).

250

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 04/05/2025

Excited to attend my first RLDM! (fomo from missing the past 2). Would love to say hi -- and will be looking for Talk RL Podcast interviews 🌸🍒🌸

040

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 03/05/2025

New ideas welcome! (*Must be within 2 std dev of Normal Science.)

030

Reposted by Robin Ranjit Singh Chauhan

Justin Wolfers @justinwolfers.bsky.social · 29/04/2025

"I'm going to govern in econometrics" is a winning campaign slogan for the ages.

201371263

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 27/04/2025

Attacking ppl like you, who I see as against gatekeeping and for responsible use, is ironic - But sadly mob mentality won't care. I hope moderation can protect bluesky, its been fantastic overall as X descends.

110

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 06/04/2025

"perturbing functions" general approach for multitask, hidden parameter mdp, and multiagent: nice

010

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 10/03/2025

- @vthoma.bsky.social of @eth-ai-center.bsky.social : Contextual Bilevel RL for Incentive Alignment - Haozhe (Tony) Chen & Ang (Leon) Li @columbiauniversity.bsky.social : QGym for Queuing Network Control

140

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 10/03/2025

E65: NeurIPS 2024 – Posters and Hallways 3 - Claire Bizon Monroc of Inria : WFCRL for Wind Farm Control Andrew Wagenmaker of @ucberkeleyofficial.bsky.social : Leveraging Simulation to Bridge Sim-to-Real Gap - @harwiltz.bsky.social of @mila-quebec.bsky.social : Multivariate Distributional RL (cont)

132

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 06/03/2025

Alas @skiandsolve.bsky.social I could only share a tiny (and biased) sample! Biased towards things I am better able to understand, and nearly all theoretical work is over my head 😅

110

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 06/03/2025

Thanks! I tried looking for his bluesky but didnt find it

000

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 06/03/2025

How much would you say the field understands about the effects of bringing genes in from another organism? Is it basically an empirical science, should we expect unknown/latent/deleterious effects would be common etc

240

Robin Ranjit Singh Chauhan @robinchauhan.bsky.social · 06/03/2025

- @glenberseth.bsky.social of MILA: Reducing Value & Policy Churn in Deep RL - Alexander Rutherford of Oxford: JaxMARL – Multi-Agent RL in JAX

220