Fetching the paper…
Reading the bibliography…
We study the following question in the context of imitation learning for continuous control: how are the underlying stability properties of an expert policy reflected in the sample-complexity of an imitation learning task? We provide the first results showing that a surprisingly granular connection can be made between the underlying expert system's incremental gain stability, a novel measure of robust convergence between pairs of system trajectories, and the dependency on the task horizon $T$ of the resulting generalization bounds.
Alvinn: An autonomous land vehicle in a neural network
Dean A. Pomerleau · 1989
Earlier work this paper cites.
Robust and optimal control
Kemin Zhou, John C. Doyle, and Keith Glover · 1996
Earlier work this paper cites.
On contraction analysis for non-linear systems
Winfried Lohmiller and Jean-Jacques E. Slotine · 1998
Earlier work this paper cites.
Is imitation learning the route to humanoid robots?
Stefan Schaal · 1999
Earlier work this paper cites.
Rademacher and gaussian complexities: Risk bounds and structural results
Peter L. Bartlett and Shahar Mendelson · 2002
Earlier work this paper cites.
Analysis of discrete and hybrid stochastic systems by nonlinear contraction theory
Quang-Cuong Pham · 2008
Earlier work this paper cites.
Efficient reductions for imitation learning
Stéphane Ross and J. Andrew Bagnell · 2010
Earlier work this paper cites.
A reduction of imitation learning and structured prediction to no-regret online learning
Stéphane Ross, Geoffrey J. Gordon, and J. Andrew Bagnell · 2011
Earlier work this paper cites.
A course in robust control theory: a convex approach , volume 36
Geir E. Dullerud and Fernando Paganini · 2013
Earlier work this paper cites.
Neural learning of vector fields for encoding stable dynamical systems
Andre Lemme, Klaus Neumann, R. Felix Reinhart, and Jochen J. Steil · 2014
Earlier work this paper cites.
Trust region policy optimization
John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz · 2015
Earlier work this paper cites.
Incremental stability properties for discrete-time systems
Duc N. Tran, Björn S. Rüffer, and Christopher M. Kellett · 2016
Earlier work this paper cites.
Imitation learning: A survey of learning methods
Ahmed Hussein, Mohamed M. Gaber, Eyad Elyan, and Chrisina Jayne · 2017
Earlier work this paper cites.
Deeply aggrevated: Differentiable imitation learning for sequential prediction
Wen Sun, Arun Venkatraman, Geoffrey J. Gordon, Byron Boots, and J. Andrew Bagnell · 2017
Earlier work this paper cites.
Dropoutdagger: A bayesian approach to safe imitation learning
Kunal Menda, Katherine Driggs-Campbell, and Mykel J. Kochenderfer · 2017
Cited alongside, same era.
Learning partially contracting dynamical systems from demonstrations
Harish Ravichandar, Iman Salehi, and Ashwin Dani · 2017
Cited alongside, same era.
Dart: Noise injection for robust imitation learning
Michael Laskey, Jonathan Lee, Roy Fox, Anca Dragan, and Ken Goldberg · 2017
Cited alongside, same era.
An algorithmic perspective on imitation learning
Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J. Andrew Bagnell, Pieter Abbeel, and Jan Peters · 2018
Cited alongside, same era.
Learning an approximate model predictive controller with guarantees
Michael Hertneck, Johannes Köhler, Sebastian Trimpe, and Frank Allgöwer · 2018
Cited alongside, same era.
End-to-end driving via conditional imitation learning
Neural lyapunov control
Ya-Chien Chang, Nima Roohi, and Sicun Gao · 2019
Later among the works it cites.
High-Dimensional Statistics: A Non-Asymptotic Viewpoint
Martin J. Wainwright · 2019
Later among the works it cites.
Imitation learning with stability and safety guarantees
He Yin, Peter Seiler, Ming Jin, and Murat Arcak · 2020
Later among the works it cites.
Generalization guarantees for imitation learning
Allen Z. Ren, Sushant Veer, and Anirudha Majumdar · 2020
Later among the works it cites.
Learning stabilizable nonlinear dynamics with contraction-based regularization
Sumeet Singh, Spencer M. Richards, Vikas Sindhwani, Jean-Jacques E. Slotine, and Marco Pavone · 2020
Later among the works it cites.
Beyond convexity—contraction and global convergence of gradient descent
Patrick M. Wensing and Jean-Jacques E. Slotine · 2020
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Felipe Codevilla, Matthias Miiller, Antonio López, Vladlen Koltun, and Alexey Dosovitskiy · 2018
Cited alongside, same era.
Safe end-to-end imitation learning for model predictive control
Keuntaek Lee, Kamil Saigol, and Evangelos A. Theodorou · 2018
Cited alongside, same era.
Learning contracting vector fields for stable imitation learning
Vikas Sindhwani, Stephen Tu, and Mohi Khansari · 2018
Cited alongside, same era.
JAX: composable transformations of Python+NumPy programs, 2018
James Bradbury, Roy Frostig, Peter Hawkins, Matthew James Johnson, Chris Leary, Dougal Maclaurin, George Necula, Adam Paszke, Jake VanderPlas, Skye Wanderman-Milne, and Qiao Zhang · 2018
Cited alongside, same era.
Dynamic locomotion in the mit cheetah 3 through convex model-predictive control
Jared Di Carlo, Patrick M. Wensing, Benjamin Katz, Gerardo Bledt, and Sangbae Kim · 2018
Cited alongside, same era.
Ensembledagger: A bayesian approach to safe imitation learning
Kunal Menda, Katherine Driggs-Campbell, and Mykel J. Kochenderfer · 2019
Cited alongside, same era.
Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees
Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, and Tengyu Ma · 2019
Cited alongside, same era.
Later among the works it cites.
Haiku: Sonnet for JAX, 2020
Tom Hennigan, Trevor Cai, Tamara Norman, and Igor Babuschkin · 2020
Later among the works it cites.
Optax: composable gradient transformation and optimisation, in jax!, 2020
Matteo Hessel, David Budden, Fabio Viola, Mihaela Rosca, Eren Sezener, and Tom Hennigan · 2020
Later among the works it cites.
Probably approximately correct constrained learning
Luiz Chamon and Alejandro Ribeiro · 2020
Later among the works it cites.
Learning stability certificates from data
Nicholas M. Boffi, Stephen Tu, Nikolai Matni, Jean-Jacques E. Slotine, and Vikas Sindhwani · 2020
Later among the works it cites.
Approximation of lyapunov functions from noisy data
Peter Giesl, Boumediene Hamzi, Martin Rasmussen, and Kevin Webster · 2020
Later among the works it cites.
Pybullet, a python module for physics simulation for games, robotics and machine learning
Erwin Coumans and Yunfei Bai · 2021
Closest in time.
Regret bounds for adaptive nonlinear control
Nicholas M. Boffi, Stephen Tu, and Jean-Jacques E. Slotine · 2021
Closest in time.