nathan monette

Excited to announce my first paper, with @j_foerst and @FLAIR_Ox, was accepted into @rl_conference 2025! We establish a new UED method called NCC that obtains strong performance based on principles of optimisation theory.

He's terrible. Screwed my buddy sgd.

reinforcement learning infrastructure

1/ 🕵️ Algorithm discovery could lead to huge AI breakthroughs! But what is the best way to learn or discover new algorithms? I'm so excited to share our brand new @rl_conference paper which takes a step towards answering this! 🧵

you can change history with an 11-page paper

*New AI Alignment Paper* 🚨 Goal misgeneralization occurs when AI agents learn the wrong reward function, instead of the human's intended goal. 😇 We show that training with a minimax regret objective provably mitigates it, promoting safer and better-aligned RL policies!

🚀 Excited to announce Hyperoptax, a library for parallel hyperparameter tuning in JAX. Implements Grid, Random, and Bayesian search in pure JAX so that you can rapidly search across parameter configurations in parallel ‖. 📦 pip install hyperoptax github.com/TheodoreWolf/h…

Antiviral therapy design is myopic 🦠🙈 optimised only for the current strain. That's why you need a different Flu vaccine every year! Our #ICML2025 paper ADIOS proposes "shaper therapies" that steer viral evolution in our favour & remain effective. Work done @FLAIR_Ox 🧵👇

Theory of Mind (ToM) is crucial for next gen LLM Agents, yet current benchmarks suffer from multiple shortcomings. Enter 💽 Decrypto, an interactive benchmark for multi-agent reasoning and ToM in LLMs! Work done with @TimonWilli & @j_foerst at @AIatMeta & @FLAIR_Ox 🧵👇

Had a blast together with @how_uhh at @LeRobotHF hackathon this weekend. Built phone-based teleoperation for my SO-100 arm using pose estimation. Here’s a quick BTS of the final demo with teleop working (+ a small victory dance 🎉)

True dat

I am afraid to report, RL works.

So many incredible, inspiring ideas in @_rockt’s keynote…. But my personal favorite slide was a clarification on the world model definition 😱

FLAIR is at ICLR 🇸🇬 Find out our schedule for the week 👇

Our new paper (first one of my PhD!) on cooperative AI reveals a surprising insight: Environment Diversity > Partner Diversity. Agents trained in self-play across many environments learn cooperative norms that transfer to humans on novel tasks. shorturl.at/fqsNN🧵