Ryan Hoque

I am a Robotics Research Scientist at Apple ML Research. I received my PhD from UC Berkeley, where I was advised by Ken Goldberg in the Berkeley Artificial Intelligence Research (BAIR) lab. I have also been fortunate to collaborate with researchers from Google DeepMind, NVIDIA SRL, Meta FAIR, Honda Research Institute, Siemens AI, and Uber ATG (acq. Aurora). My research primarily consists of scalable algorithms for robot imitation learning.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Twitter

My research has been focused on the development of imitation learning and reinforcement learning algorithms that scale to large robot fleets, especially in the context of robotic manipulation. Recently this includes efforts to train large vision-language-action models for general-purpose manipulation (e.g., RT-X). I have also worked on learning algorithms for robotic manipulation of deformable objects. In addition to selected publications below (see my CV for the full list), check out:

• My dissertation talk, a 45-minute summary of my PhD research accessible to both researchers and the general public.
• My written dissertation, the entirety of my PhD research in 197 pages.
• My talk at CoRL 2022 in Auckland, New Zealand and BAIR Blog post on Interactive Fleet Learning.
• Issue #238 of the Import AI newsletter featuring my Master's research on manipulating deformable objects.
• University courses that have featured my research, including CS 16-881: Deep Reinforcement Learning for Robotics at Carnegie Mellon University, CS 6960: Human-AI Alignment at the University of Utah, and CS 343: Artificial Intelligence at the University of Texas, Austin.

(In collaboration with Google DeepMind and 33 academic labs) Cross-embodiment fleet learning with heterogeneous robots. An open-source dataset of 1M+ robot trajectories from 22 robot embodiments, and results with robot foundation models trained on this data.

A state-of-the-art robot-gated interactive imitation learning algorithm that reasons about both state novelty and risk to actively query for human interventions more efficiently than prior algorithms.

We introduce new formalism, algorithms, and open-source benchmarks for "Interactive Fleet Learning": interactive learning with multiple robots and multiple humans.

(In collaboration with NVIDIA SRL) A data generation system extending MimicGen to the interactive imitation learning setting, improving policy robustness up to 39x with a data budget of only 10 human interventions.

An extension of Interactive Fleet Learning to heterogeneous and multimodal human supervision, including a novel approach for quantifying uncertainty in energy-based models.

(In collaboration with Google DeepMind) We perform the first systematic benchmarking of fabric manipulation algorithms with Google Reach, a prototype hardware testbed for low-latency remote robot control over the Internet.

(In collaboration with Honda Research Institute) A novel model-based reinforcement learning technique that trains a visual dynamics model for sequentially manipulating fabric toward a variety of goal images, entirely from random interaction RGBD data in simulation.

I'm a Bay Area native and a lifelong bear: I received my B.S., M.S., and Ph.D. in EECS at UC Berkeley in a single stretch of 8 years. Outside of research, I have an eclectic mix of hobbies including playing piano covers of heavy metal bands, reading and writing about philosophy (especially metaphysics), traveling, and enjoying the outdoors. For the philosophically inclined, I wrote an essay in 2020 in which I synthesize Western and Eastern thought to answer the age-old "meaning of life" question. I'm currently working on a significantly improved revision as a full-length book, but it's still in progress...!

Website template from BAIR alum Jon Barron.