1 citations · 3 across the 4 of their papers we have counts for
4 papers
Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio +4
Recent advances in learning decision-making policies can largely be attributed to training expressive policy models, largely via imitation learning. While imitation learning discar…
Bimanual Dexterity for Complex Tasks
Kenneth Shaw, Yulong Li, Jiahui Yang +5
To train generalist robot policies, machine learning methods often require a substantial amount of expert human teleoperation data. An ideal robot for humans collecting data is one…
HRP: Human Affordances for Robotic Pre-Training
Mohan Kumar Srirama, Sudeep Dasari, Shikhar Bahl +1
In order to *generalize* to various tasks in the wild, robotic agents will need a suitable representation (i.e., vision network) that enables the robot to predict optimal actions g…
An Unbiased Look at Datasets for Visuo-Motor Pre-Training
Sudeep Dasari, Mohan Kumar Srirama, Unnat Jain +1
Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by…