Learning Partially Contracting Dynamical Systems from Demonstrations

67 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Recent Advances in Robot Learning from Demonstration (2020, background): “However, other generalized definitions of distance might be more appropriate for a given task (94, 110).”
Learning position and orientation dynamics from demonstrations via contraction analysis (2018, background): “…a non-expert programmer should be able to program the robot by demonstrating the task to the robot (Rossano et al. 2013; Ravichandar and Dani 2015; Ravichandar et al. 2016, 2017; Koenig and Matari´c 2016), or in the case of robots assisting the elderly, the user should be able to teach the robots…”
On the Sample Complexity of Stability Constrained Imitation Learning (2021, unknown): “As demonstrated empirically in (Lemme et al., 2014; Ravichandar et al., 2017; Sindhwani et al., 2018; Singh et al., 2020), using such stability-based regularizers to trim the hypothesis space results in more data-efficient and robust learning algorithms – however, no quantitative sample-complexity b”