Research
I am broadly interested in Robotics, Reinforcement Learning, and NLP. My motivation is to build
agents with cognitive capabilities that can learn and infer like humans.
|
|
Train Offline, Test Online: A Real Robot Learning Benchmark
Gaoyue Zhou*, Victoria Dean*, Mohan Kumar Srirama, Aravind Rajeswaran, Jyothish Pari,
Kyle Hatch, Aryan Jain, Tianhe Yu, Pieter Abbeel, Lerrel Pinto, Chelsea Finn, Abhinav Gupta
Accepted to ICRA 2023
Best Paper Award at NeurIPS WBRC 2022
OpenReview
|
video |
project page
We introduce a new benchmark for tabletop manipulation: Train Offline, Test Online (TOTO) and
showed performance of state-of-the-art models on two tasks.
|
|
Real World Offline Reinforcement Learning with Realistic Data Source
Gaoyue Zhou*, Liyiming Ke*, Siddhartha Srinivasa, Abhinav Gupta, Aravind Rajeswaran,
Vikash Kumar
Accepted to ICRA 2023 and 3 NeurIPS 2022 workshops
arXiv |
video |
project page
In this work, we evaluate Offline RL algorithms' performance on real robot, on in-domain tasks and
transfer learning settings.
|
|
Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia
Samee Ibraheem*, Gaoyue Zhou*, John DeNero
Annual Conference of the North American Chapter of the Association for Computational Linguistics
(NAACL), 2022
Oral Presentation
arXiv |
video
|
project page
In this paper, we collect and release a dataset for identifying deceptive actors through the game
of Mafia, as well as train models to identify such actors and reveal features of their language.
|
|
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
Avi Singh*, Huihan Liu*, Gaoyue Zhou, Albert Yu, Nicholas Rhinehart, Sergey Levine
International Conference on Learning Representations (ICLR), 2021
Oral Presentation (top 1.8% of submissions)
arXiv |
video |
project page
We proposed a method for pre-training a behavioral prior for reinforcement learning using data
from a diverse range of tasks, and used this behavioral prior to speed up learning of new tasks.
|
|
Modeling Eva Hild's Sculpture "Wholly"
Advised by Prof. Carlo H. Séquin
tech report
We proposed various ways to use CAD Tools for the Procedural Generation of 2-Manifold Sculpture
Geometries with high-level control.
|
|