384 citations · 1.5k across the 50 of their papers we have counts for
12 papers · 1 filter
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency
Qiang Zhang, Tete Xiao, Alexei A. Efros +2
At the heart of many robotics problems is the challenge of learning correspondences across domains. For instance, imitation learning requires obtaining correspondence between human…
Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation
Albert Zhan, Ruihan Zhao, Lerrel Pinto +2
Recent advances in unsupervised representation learning significantly improved the sample efficiency of training Reinforcement Learning policies in simulated environments. However,…
Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
Bryan Chen, Alexander Sax, Gene Lewis +5
Vision-based robotics often separates the control loop into one module for perception and a separate module for control. It is possible to train the whole system end-to-end (e.g. w…
Visual Imitation Made Easy
Sarah Young, Dhiraj Gandhi, Shubham Tulsiani +3
Visual imitation learning provides a framework for learning complex manipulation behaviors by leveraging human demonstrations. However, current interfaces for imitation such as kin…
Swoosh! Rattle! Thump! -- Actions that Sound
Dhiraj Gandhi, Abhinav Gupta, Lerrel Pinto
Truly intelligent agents need to capture the interplay of all their senses to build a rich physical understanding of their world. In robotics, we have seen tremendous progress in u…
Self-Supervised Policy Adaptation during Deployment
Nicklas Hansen, Rishabh Jangir, Yu Sun +5
In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, gener…