Abhishek Gupta
@abhishekunique7.bsky.social
Assistant Professor, Paul G. Allen School of Computer Science and Engineering, University of Washington
Visiting Faculty, NVIDIA
Ph.D. from Berkeley, Postdoc MIT
https://homes.cs.washington.edu/~abhgupta
I like robots and reinforcement learning :)
Visiting Faculty, NVIDIA
Ph.D. from Berkeley, Postdoc MIT
https://homes.cs.washington.edu/~abhgupta
I like robots and reinforcement learning :)
Reposted by Abhishek Gupta
UW News put out a Q&A about our recent work on Variational Preference Learning, a technique for personalizing Reinforcement Learning from Human Feedback (RLHF) washington.edu/news/2024/12...
Q&A: New AI training method lets systems better adjust to users’ values
University of Washington researchers created a method for training AI systems — both for large language models like ChatGPT and for robots — that can better reflect users’ diverse values. It...
washington.edu
December 18, 2024 at 9:51 PM
UW News put out a Q&A about our recent work on Variational Preference Learning, a technique for personalizing Reinforcement Learning from Human Feedback (RLHF) washington.edu/news/2024/12...
We’ve been investigating how sim, while wrong, can be useful for real-world robotic RL! In our #NeurIPS2024 work, we theoretically showed how naive sim2real transfer can be inefficient, but if you *learn to explore* in sim, this transfers to the real world! We show this works on real robots! 🧵(1/6)
December 6, 2024 at 12:46 AM
We’ve been investigating how sim, while wrong, can be useful for real-world robotic RL! In our #NeurIPS2024 work, we theoretically showed how naive sim2real transfer can be inefficient, but if you *learn to explore* in sim, this transfers to the real world! We show this works on real robots! 🧵(1/6)
I'm excited about scaling up robot learning! We’ve been scaling up data gen with RL in realistic sims generated from crowdsourced videos. Enables data collection far more cheaply than real world teleop. Importantly, data becomes *cheaper* with more environments and transfers to real robots! 🧵 (1/N)
December 5, 2024 at 2:13 AM
I'm excited about scaling up robot learning! We’ve been scaling up data gen with RL in realistic sims generated from crowdsourced videos. Enables data collection far more cheaply than real world teleop. Importantly, data becomes *cheaper* with more environments and transfers to real robots! 🧵 (1/N)