36 citations · 203 across the 30 of their papers we have counts for
Showing 2023 · cs.ROShow all
2 papers · 2 filters
cs.RO2023
Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration
Sayantan Auddy, Sebastian Bergner, Justus Piater
In continual learning from demonstration (CLfD), a robot learns a sequence of real-world motion skills continually from human demonstrations. Recently, hypernetworks have been succ…
cs.RO2023★ 3 cited
Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model
Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano +2
Robots capable of learning from demonstration (LfD) must exhibit stability while executing learned motion skills. To be effective in the real world, they should also remember multi…