Thrilled to announce the first annual Reinforcement Learning Conference RL_Conference, which will be held at UMass Amherst August 9-12! RLC is the first strongly peer-reviewed RL venue with proceedings, and our call for papers is now available: rl-conference.cc.

And come see our spotlight on decision-pretrained transformer at 10:45am Tuesday in the great hall or our poster #13 in b1-b2 level 1! Work lead by Jonathan Lee and Annie Xie w Chelsea Finn Aldo Pacchiano Ofir Nachum

Curious about contextual bandits with theoretical bounds that balance cumulative regret and simple regret? Come check out Sanath’s poster : Wed 10:45 am - Great Hall and Hall B1+B2 (level 1) #1914. Jt w Susan Athey and Ruohan Zhan arxiv.org/abs/2307.02108 #NeurIPS2023

Come talk about experimental design for contextual bandits! Led by Aldo Pacchiano w Jonathan Lee. Wednesday 5pm - Great Hall & Hall B1+B2 (level 1) #1923 #NeurIPS2023

Can we use SL for RL, even when the task requires “stitching”? See our NeurIPS paper “Waypoint Transformer: RL via SL with Intermediate Targets” Led by Anirudhan Badrinath w Y Flet-Barliac + A Nie. Also today Goal-Conditioned RL rm 206-207; 4:30-5:30 pm shorturl.at/xX023

Excited to be part of this along with Anna Goldie eytan bakshy Nathan Kallus Michaela Van der Schar and more! My talk is at 1:20pm rm 208-210 today #NeurIPS2023

One of the best parts of #NeurIPS2023– thanks to Pablo Samuel Castro for organizing!

Thanks bethanie maples ! It was great to be there and talk about work like that lead by great students Allen Nie and Evan Liu w/faculty collaborators Chris Piech and Chelsea Finn arxiv.org/abs/2211.08802

Please retweet: My students are recruiting participants for a study on technology to support physical activity. If you are interested in getting more exercise and own an iPhone, please fill out our screening survey: bit.ly/physical-activ…

Excited for season 2 from uɐᴉɹoʞᴉɹʞ ᴉɟɟɐɹ👨🏼‍🚀 → @[email protected] about data, privacy and hopefully still some reasons to be technically optimistic podcasts.apple.com/us/podcast/tec…

We are releasing our preprint of a large-scale study about LLM’s effect on learning. We recruited 8.7k students from 146 countries to learn programming, offering them LLMs and evaluating whether their exam performance increased in an RCT. 1/🧵 🎓: osf.io/preprints/osf/…

I'm excited to share our new paper exploring how LLM chatbots can be used to motivate physical activity behavior change! Check out our pre-print on arXiv: arxiv.org/abs/2405.06061

It’s wonderful to be part of HAI. @Allen_A_N will be sharing some of our HAI work on reinforcement learning for education at the lunch poster session— representing collaborations with many fantastic colleagues incl Chelsea Finn James Landay Chris Piech. #stanfordhai

Loved doing this yesterday before a great day of reinforcement learning at RL_Conference!

I had the pleasure of co-advising Andrea with Mykel Kochenderfer SISL for a PhD-- this is a great opportunity!

We’ve released updated 2024 lectures from my Stanford RL CS234 class! shorturl.at/pf427 This includes a guest lecture on Direct Preference Optimization (DPO) from 1st authors Rafael Rafailov @ NeurIPS Archit Sharma Eric tinyurl.com/3kr4czth Thanks to Stanford Online!

Stanford's "Reinforcement Learning" by Emma Brunskill (Spring 2024) 📽️ Lecture Videos: youtube.com/playlist?list=… 🗒️ Course Website: web.stanford.edu/class/cs234/CS…

Come join us!

"On a weekly basis more than 90% of people use weather forecasts, job market reports, food safety warnings and other information that is based on federal science." npr.org/2025/05/06/nx-… Federally-funded science benefits us all.

Super exciting work Jonathan Lee -- congrats to you and the whole team!