🤖 Robots must understand and act upon instructions given by humans through various forms (videos, text, speech, images) to collaborate efficiently. We present MUTEX: Learning Unified Policies from Multimodal Task Specifications. #CoRL2023 🌐: ut-austin-rpl.github.io/MUTEX 1/n

Some work from my time Georgia Tech on generalizing heterogeneous multi-robot policies to new team sizes, compositions and even robots! Stop by at poster session 6 Conference on Robot Learning

I will be at NeurIPS Conference 2023 to present my work f-Policy Gradients (arxiv.org/abs/2310.06794…). Do check out my poster on December 13th, 10.45 am CST in Great Hall & Hall B1 + B2. Happy to chat about the work and RL in general. DMs are open to anyone who wants to chat or meet.

Thanks to Ben Eysenbach, this (partial) list of senior women in RL means you should never have an unbalanced panel or speaker list again

🚀 Despite efforts to scale up Behavior Cloning for Robots, large-scale BC has yet to live up to its promise. How can we break through the performance plateau? Introducing 🔥FLaRe: fine-tuning large-scale robot policies with Reinforcement Learning. robot-flare.github.io 🧵

🚀 I am recruiting PhD students for Fall 2025 at the UCLA Robot Intelligence Lab! 🤖 If you are interested in robot learning and human-robot interaction, mark me as a potential adivisor when you apply to the UCLA CS PhD program! #PhD #Robotics UCLA CS Department

When Harshit Sikchi (will be at NeurIPS 25) described this project, I knew it was going to be very cool. Is the future here?

We ran thousands of sweeps to compare RL algos for imperfect information games and found preliminary evidence for the Policy Gradient Hypothesis: With proper tuning, generic PG (PPO, etc.) methods are highly competitive in IIGS. Check out the full paper: arxiv.org/abs/2502.08938

In the past few days, I’ve spent way more time playing tic-tac-toe than I expected. Very cool demo from Nathan that showcases our policies.

Hiring researchers and engineers for a stealth, applied research company with a focus on RL x foundation models. Folks on the team already are leading RL / learning researchers. If you think you'd be good at the research needed to get things working in practice, email me

Successfully defended my Ph.D. today 🎓🥳! Scott Niekum and Amy Zhang are the best advisors I could have ever asked for. A big thanks to my committee members Marc G. Bellemare Yuke Zhu Peter Stone . The full presentation video will be uploaded soon... Excited about what's

An incredible defense!

Missed the NeurIPS deadline? RLBrew Workshop deadline in less than 15 days. Submit your finished or unfinished work to this RLC workshop.

Come on down and get some RLBrewskies with us!

RLZero will be presented at NeurIPS Conference 2025 . Learn more about the work in the thread below:

Very cool work! The human video-to-robot behavior gap is a tough one to bridge!

Go see Harshit talk about this work! I think its one of the coolest projects i've been involved with during my PhD thus far.

Loved working with Akhil Bagaria et al.! Some amazing applications of RL to real world problems that we all want! Highly recommend!