Next week! 🎆 At #colt2026, @optimistsinc.bsky.social, @ericeaton.bsky.social, @surbhigoel.bsky.social, @marcelhussing.bsky.social, @mkearnsphilly.bsky.social, @aaroth.bsky.social, and @sikatasengupta.bsky.social will present “Model Agreement via Anchoring”... 🧵 (1/3)

Model Agreement via Anchoring

Numerous lines of aim to control $\textit{model disagreement}$ -- the extent to which two machine learning models disagree in their predictions. We adopt a simple and standard notion of model disagree...

arxiv.org

Why do all LLMs predict 27 as their favorite number? There may be a principled explanation. Learn more at Agents in the Wild at #ICLR2026. @ericeaton.bsky.social, me, @surbhigoel.bsky.social, @mkearnsphilly.bsky.social, @aaroth.bsky.social, @sikatasengupta.bsky.social, @optimistsinc.bsky.social

Time for round number two. Stop by #4406 to learn about stability guarantees in RL. #ICLR2026 @ericeaton.bsky.social @mkearnsphilly.bsky.social @aaroth.bsky.social @sikatasengupta.bsky.social @optimistsinc.bsky.social

In “Replicable Reinforcement Learning with Linear Function Approximation,” @optimistsinc.bsky.social, @marcelhussing.bsky.social, @mkearnsphilly.bsky.social, @aaroth.bsky.social, @sikatasengupta.bsky.social, & more develop replicable methods for linear function approximation in RL: (5/12)

Replicable Reinforcement Learning with Linear Function Approximation

Replication of experimental results has been a challenge faced by many scientific disciplines, including the field of machine learning. Recent work on the theory of machine learning has formalized rep...

arxiv.org

The paper is here: arxiv.org/abs/2602.23360 and is joint work with Eric Eaton, @surbhigoel.bsky.social, @marcelhussing.bsky.social, @mkearnsphilly.bsky.social, @sikatasengupta.bsky.social and @optimistsinc.bsky.social

The other paper accepted to @iclr-conf.bsky.social 2026 🇧🇷. Our work on replicable RL sheds some light on how to consistently make decisions in RL. @ericeaton.bsky.social @mkearnsphilly.bsky.social @aaroth.bsky.social @sikatasengupta.bsky.social @optimistsinc.bsky.social

Marcel Hussing@marcelhussing.bsky.social · 9mo ago

I think I posted about it before but never with a thread. We recently put a new preprint on arxiv. 📖 Replicable Reinforcement Learning with Linear Function Approximation 🔗 arxiv.org/abs/2509.08660 In this paper, we study formal replicability in RL with linear function approximation. The... (1/6)

Excited to be visiting #UPenn for the CS Theory Seminar tomorrow (Nov 21), where I’ll present my recent work on pure exploration in reinforcement learning, done together with @aldopacchiano.bsky.social Many thanks to @sikatasengupta.bsky.social for organizing this!

I think I posted about it before but never with a thread. We recently put a new preprint on arxiv. 📖 Replicable Reinforcement Learning with Linear Function Approximation 🔗 arxiv.org/abs/2509.08660 In this paper, we study formal replicability in RL with linear function approximation. The... (1/6)

Replicable Reinforcement Learning with Linear Function Approximation

Replication of experimental results has been a challenge faced by many scientific disciplines, including the field of machine learning. Recent work on the theory of machine learning has formalized rep...

arxiv.org

Come say hi at our #ICML poster today during Poster Session 1 (W-600)! Joint work with @ericeaton.bsky.social @marcelhussing.bsky.social @optimistsinc.bsky.social @aaroth.bsky.social @mkearnsphilly.bsky.social! arxiv.org/abs/2502.11828

Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces

In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it ...

arxiv.org

hi bluesky 👋 I’m starting a blog! First post on how I use GenAI in my workflow as an academic. give it a read + tell me what you think: yeganeha.substack.com/p/academic-p... #GenAI #Academia

Academic Productivity with GenAI: A Researcher’s Guide

My Everyday Use of GenAI as a Researcher

yeganeha.substack.com

Dhruv Rohatgi will be giving a lecture on our recent work on comp-stat tradeoffs in next-token prediction at the RL Theory virtual seminar series (rl-theory.bsky.social) tomorrow at 2pm EST! Should be a fun talk---come check it out!!

Dylan Foster 🐢@djfoster.bsky.social · last yr.

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier arxiv.org/abs/2502.12465 New paper (another fun internship project!) with Dhruv Rohatgi, Adam Block, Audrey Huang (ahahaudrey.bsky.social), and Akshay Krishnamurthy (akshaykr.bsky.social). 1/11

Later today, Sikata and Marcel will talk about their recent work on oracle-efficient RL with ensembles. Join us!

Last seminars before the summer break: 04/29: Max Simchowitz (CMU) 05/06: Jeongyeol Kwon (Univ. of Widsconsin-Madison) 05/20: Sikata Sengupta & Marcel Hussing (Univ. of Pennsylvania) 05/27: Dhruv Rohatgi (MIT) 06/03: David Janz (Univ. of Oxford) 06/10: Nneka Okolo (MIT)

@mkearnsphilly.bsky.social is now on bsky as well!

Sikata Sengupta@sikatasengupta.bsky.social · 2y ago

If you are at #NeurIPS, we will be presenting this work (#6610) from 4:30-7:30PM today and would love to chat! @marcelhussing.bsky.social @optimistsinc.bsky.social @aaroth.bsky.social

If you are at #NeurIPS, we will be presenting this work (#6610) from 4:30-7:30PM today and would love to chat! @marcelhussing.bsky.social @optimistsinc.bsky.social @aaroth.bsky.social

Marcel Hussing@marcelhussing.bsky.social · 2y ago

Actual content post: Have not talked much about this work yet but we have a paper on Oracle-Efficient Reinforcement Learning for Max Value Ensembles at this year's #NeurIPS. We provide an efficient algorithm to ensemble policies given a value function oracle. arxiv.org/abs/2405.16739

I made a starter pack for learning theory people to gather some people around the topic. There are too many names on here that I don't know so I only added a few I do. If you believe you should be on this list, let me know. I will add people with accurate profile descriptions. go.bsky.app/21nFz12

Actual content post: Have not talked much about this work yet but we have a paper on Oracle-Efficient Reinforcement Learning for Max Value Ensembles at this year's #NeurIPS. We provide an efficient algorithm to ensemble policies given a value function oracle. arxiv.org/abs/2405.16739

Oracle-Efficient Reinforcement Learning for Max Value Ensembles

Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardina...

arxiv.org