no code implementations • 12 Oct 2022 • Gaoyue Zhou, Liyiming Ke, Siddhartha Srinivasa, Abhinav Gupta, Aravind Rajeswaran, Vikash Kumar
Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience.
no code implementations • 13 Nov 2020 • Liyiming Ke, Jingqiang Wang, Tapomayukh Bhattacharjee, Byron Boots, Siddhartha Srinivasa
Billions of people use chopsticks, a simple yet versatile tool, for fine manipulation of everyday objects.
no code implementations • 30 May 2019 • Liyiming Ke, Sanjiban Choudhury, Matt Barnes, Wen Sun, Gilwoo Lee, Siddhartha Srinivasa
We show that the state-of-the-art methods such as GAIL and behavior cloning, due to their choice of loss function, often incorrectly interpolate between such modes.
1 code implementation • CVPR 2019 • Liyiming Ke, Xiujun Li, Yonatan Bisk, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, Siddhartha Srinivasa
We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et.
Ranked #3 on Vision-Language Navigation on Room2Room