2 citations · 2 across the 2 of their papers we have counts for
6 papers
A Simple Approach to Continual Learning by Transferring Skill Parameters
K. R. Zentner, Ryan Julian, Ujjwal Puri +2
In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will…
Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning
K. R. Zentner, Ryan Julian, Ujjwal Puri +2
We explore possible methods for multi-task transfer learning which seek to exploit the shared physical structure of robotics tasks. Specifically, we train policies for a base set o…
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
Yevgen Chebotar, Karol Hausman, Yao Lu +8
We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a se…
Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme +3
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potent…
Simulator Predictive Control: Using Learned Task Representations and MPC for Zero-Shot Generalization and Sequencing
Zhanpeng He, Ryan Julian, Eric Heiden +5
Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing…
Scaling simulation-to-real transfer by learning composable robot skills
Ryan Julian, Eric Heiden, Zhanpeng He +5
We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simu…