no code implementations • 23 Oct 2023 • Jingyun Yang, Max Sobol Mark, Brandon Vu, Archit Sharma, Jeannette Bohg, Chelsea Finn
We aim to enable this paradigm in robotic reinforcement learning, allowing a robot to learn a new task with little human effort by leveraging data and models from the Internet.
no code implementations • 3 Jan 2023 • Yicong Li, Yang Tan, Jingyun Yang, Yang Li, Xiao-Ping Zhang
Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance.
no code implementations • 28 Jun 2022 • Rika Antonova, Jingyun Yang, Krishna Murthy Jatavallabhula, Jeannette Bohg
In this work, we study the challenges that differentiable simulation presents when it is not feasible to expect that a single descent reaches a global optimum, which is often a problem in contact-rich scenarios.
no code implementations • 9 Dec 2021 • Rika Antonova, Jingyun Yang, Priya Sundaresan, Dieter Fox, Fabio Ramos, Jeannette Bohg
Deformable object manipulation remains a challenging task in robotics research.
1 code implementation • ICLR 2020 • Youngwoon Lee, Jingyun Yang, Joseph J. Lim
When mastering a complex manipulation task, humans often decompose the task into sub-skills of their body parts, practice the sub-skills independently, and then execute the sub-skills together.
no code implementations • 25 Sep 2019 • Karl Pertsch, Oleh Rybkin, Jingyun Yang, Konstantinos G. Derpanis, Kostas Daniilidis, Joseph J. Lim, Andrew Jaegle
To flexibly and efficiently reason about temporal sequences, abstract representations that compactly represent the important information in the sequence are needed.
no code implementations • ICLR 2019 • Te-Lin Wu, Jaedong Hwang, Jingyun Yang, Shaofan Lai, Carl Vondrick, Joseph J. Lim
A noisy and diverse demonstration set may hinder the performances of an agent aiming to acquire certain skills via imitation learning.
no code implementations • L4DC 2020 • Karl Pertsch, Oleh Rybkin, Jingyun Yang, Shenghao Zhou, Konstantinos G. Derpanis, Kostas Daniilidis, Joseph Lim, Andrew Jaegle
We propose a model that learns to discover these important events and the times when they occur and uses them to represent the full sequence.